Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It only repeats the name and adds 'to website', with no mention of permissions, reversibility, side effects, or what 'enable' does. Score 1.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence, front-loaded, but severely under-specified for a 7-parameter configuration tool. It is concise only because it omits necessary detail. Score 2.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters, no annotations, no output schema, and many SSL siblings, the description is far too incomplete for an agent to invoke correctly. Score 1.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description mentions none of the 7 parameters (websiteId, type, enable, httpConfig, privateKey, certificate, websiteSSLId). It provides no syntax, allowed values, or meaning for any parameter. Score 1.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a verb 'Apply' and resource 'SSL to website', so the high-level purpose is discernible. However, 'apply' is vague against the many SSL siblings (obtain_ssl, upload_ssl, renew_ssl, update_https) and does not specify whether it creates, binds, or toggles SSL. Score 3.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indication of when to use this tool versus alternatives like obtain_ssl, upload_ssl, or update_https. No prerequisites or context are given. Score 2.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about permissions required, side effects, whether the Dockerfile parameter is raw content or a path, or what happens to existing images with the same name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

At two words, the text is short but under-specified rather than concise. It lacks the front-loaded actionable detail needed to help an agent invoke the tool correctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A tool with three required parameters, no annotations, and no output schema requires substantially more description. The current definition leaves the agent unable to determine how to call it correctly or what to expect in return.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for three required parameters (dockerfile, name, path). The description adds no meaning beyond the parameter names, leaving the agent with no guidance on formats, constraints, or relationships between them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description "Build image" is a tautological restatement of the tool name. It does not distinguish this operation from siblings like pull_image, load_image, commit_container, or build_openresty, nor does it specify what kind of image is being built.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as pull_image, load_image, or commit_container. The agent receives no context about prerequisites or scenarios that call for building an image from a Dockerfile.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden and delivers nothing. It does not say whether this is long-running, whether it disrupts the running service, whether it requires prior module selection, or what happens on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, but the brevity is under-specification rather than conciseness — the single parenthetical is the only detail offered and it is opaque.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a build/mutation tool with a nested required parameter, no annotations, and no output schema, the description should at minimum explain the payload shape and side effects. Almost nothing an agent needs to call it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single required 'params' nested object with 0% schema description coverage, and the description adds no information about what belongs inside it (build options, module list, version). With one undocumented, nested, required parameter, an agent cannot construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The verb+resource pair 'Build OpenResty' is identifiable, but '(XPack)' is unexplained jargon and the description does not distinguish this from the many sibling OpenResty tools (get_openresty_conf, update_openresty_module, update_openresty_by_file). An agent cannot tell whether this compiles OpenResty, installs the XPack variant, or rebuilds config from this text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indication of when to use this versus the other OpenResty configuration/module tools, nor any prerequisite (e.g., source already present, modules selected first). There are no exclusions or alternatives named despite a dense sibling set.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, yet it says nothing about whether this is a read or write operation, what authentication it needs, or what it returns. Nothing beyond the tool name is communicated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single three-word phrase is not concise-but-complete; it is under-specified. Brevity here reflects missing information rather than efficient front-loading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with an opaque nested `vars` object, no annotations, and no output schema, the description provides none of the info an agent needs. It is completely inadequate for the complexity indicated by the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both required parameters (`type` and nested `vars`) have 0% schema description coverage, and the description contributes nothing about their meaning or expected shape. For a nested-object parameter, this leaves the agent guessing at the entire input structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase "Check backup account" merely restates the tool name with the vague verb "check"; it never says what is being verified (connectivity, credentials, quota, existence). It also fails to distinguish this tool from the many sibling backup-account tools such as list_backup_accounts, get_backup_account_options, and get_backup_account_client_info.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to use this tool versus its numerous siblings, nor any prerequisites, exclusions, or alternative routing. An agent has no basis for choosing it over get_backup_account_options or list_backup_accounts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals nothing about what the check does, what it returns, whether it's read-only, or any side effects. It is completely uninformative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely terse (three words) and under-specified rather than concise. It fails to convey any meaningful information beyond the name, so its brevity is a flaw, not a virtue.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a simple tool with no parameters, no output schema, and no annotations, the description should at least state what the check entails. Instead it is completely inadequate, leaving an agent unable to predict behavior or interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the schema provides no parameter details to supplement. Per the rubric, 0 params gives a baseline of 4, and the description neither adds nor detracts from that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Check device DNS' essentially restates the tool name in sentence form, providing no additional detail about what aspect of DNS is checked or how it distinguishes from sibling tools like get_device_base_info. It is a tautology rather than a specific verb+resource statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, nor any context about prerequisites or expected scenarios. The description offers no usage instructions whatsoever.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, yet it says nothing about error behavior (throws vs. returns false for a missing file), permission requirements, or whether the path is relative to some root. The only implicit signal is that this is a non-destructive read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no filler, and the purpose is front-loaded. It is concise; the weakness is under-specification rather than verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should say what 'check' returns (a boolean, or an error on absence), and it does not. For a one-parameter existence probe this leaves a real ambiguity an agent must resolve by trial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not mention the single 'path' parameter at all, leaving its format, base directory, and validation rules undocumented. The only clue is the self-explanatory parameter name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

It gives a specific verb (check) plus a resource (file) and the exact predicate being tested (existence), so an agent knows precisely what the tool does. It does not, however, distinguish itself from siblings like get_file_size or list_files, which could also informally answer an existence question.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this rather than get_file_size, list_files, or get_file_content, and no preconditions or exclusions are given. The agent must infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the operation requires elevated privileges, whether it is reversible, how mode syntax is handled, or what happens on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded phrase with no wasted words. It is appropriately concise, though its brevity reflects under-specification rather than deliberate efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter mutation tool with no annotations, no output schema, and no schema parameter descriptions, the description is incomplete. It leaves critical details such as mode syntax, recursion via 'sub', and required permissions entirely unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for three undocumented parameters. It loosely implies that 'path' is a file and 'mode' relates to permissions, but it says nothing about mode format or the 'sub' parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Change') and resource ('file permissions'), so an agent can tell it is a permission-mutating file operation. It does not distinguish itself from siblings like chown_file or check_file, which also act on files, but the resource is clear enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as chown_file or check_file, and no prerequisites or context are stated. Usage is only implied by the tool name and resource.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and delivers almost nothing: it does not disclose permission requirements, whether the change is reversible, what happens to files not owned by the caller, or the effect of the recursive flag. Only the bare mutation intent is conveyed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words are front-loaded and waste-free, but this is not genuine conciseness so much as under-specification. A useful description for a 4-parameter mutation tool cannot fit in a phrase this short.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a filesystem mutation with 4 parameters (one required boolean whose meaning is undisclosed), no annotations, and no output schema, the description omits nearly everything an agent needs to invoke it correctly, including the meaning of 'sub' and any privilege requirements.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 4 parameters, so the description must compensate and does not. The 'user' and 'group' values are only faintly implied by 'owner', and the boolean 'sub' parameter (evidently recursive application) is left completely unexplained, as is the expected format of 'path'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Change file owner'), which is semantically clear on its own. However, it offers no scope or differentiation from the closely related sibling chmod_file (permissions vs. ownership), so an agent must infer the distinction from the tool names alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (ownership changes typically require elevated privileges/root), and no reference to alternatives such as chmod_file or move_file. The agent gets no routing help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. "Clean" weakly implies removal of records, but the description does not say what is destroyed, whether the operation is scoped (all records vs. a date range), whether it is reversible, or what permissions it needs – a significant gap for a destructive cleanup tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase with zero waste, which is structurally fine, but its brevity reflects under-specification rather than disciplined conciseness. There is no front-loaded scope or constraint to justify the extreme length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive maintenance operation with no annotations, no output schema, and no parameters, the description supplies nothing an agent needs to call it safely – no scope, no retention semantics, no confirmation of destructiveness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema defines zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter semantics could usefully be added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Clean ClamAV records" names a verb and a resource, and the "ClamAV records" scope does loosely separate it from sibling cleanup tools like clean_container_log. However, "clean" is ambiguous for a records resource – it could mean purge old records, delete all records, or sanitize them – so the agent learns the domain but not the actual operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no routing to the obviously related sibling get_clam_records or to scan_clam/get_clam_file. The agent must infer entirely from the name that this is the destructive counterpart to reading records.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it says almost nothing. It does not state whether logs are deleted permanently or truncated, whether the compose must be stopped first, whether permissions are required, or what is returned. 'Clean' hints at destructive removal but confirms nothing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase with zero padding and nothing trailing, so it is maximally brief and front-loaded. But brevity here stems from under-specification rather than disciplined editing, so it does not earn above mid-range.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating maintenance tool with no annotations, no output schema, and an undocumented required parameter, the definition is far too thin. Only the tool name supplies context; nothing about effects, safety, or return behavior is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'id' has 0% schema description coverage, so the schema offers no meaning, and the description adds none. It is not stated whether 'id' is a compose ID, an app ID, or a log ID, nor what happens on an invalid value. With one undocumented required parameter, the description fails to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase 'Clean compose log' does identify a verb and a resource, so an agent can infer it removes/truncates a compose stack's log data. However, it is essentially the tool name de-snake_cased, with no scope, no mention of which compose artifact is affected, and no differentiation from the sibling clean_container_log. Purpose is only vaguely determined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool, what preconditions apply (e.g., the compose must exist), or how it relates to adjacent tools such as clean_container_log. The agent is left to infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It says nothing about whether the operation is destructive, what gets removed, whether it is reversible, required permissions, or side effects. This is a severe gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

At three words, the description is not concise so much as under-specified. It front-loads no useful constraints, conditions, or warnings, and every sentence that would earn its place is absent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a likely destructive maintenance operation with no annotations, no parameter documentation, and no output schema, the description is completely inadequate. An agent would lack essential information to invoke it safely or correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage for its single required `id` parameter, and the description provides no meaning for it. The agent cannot tell whether `id` refers to a container ID, log ID, or something else, and must rely entirely on the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is essentially the tool name restated in title case ('Clean container log'), with no additional clarification. While it names a resource and an action, it does not explain what 'clean' means (delete, truncate, rotate) or distinguish it from siblings like `get_container_logs` or `clean_compose_log`.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, nor any mention of prerequisites or related log-retrieval tools. The description simply names the operation, leaving the agent to infer context entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full disclosure burden, yet it says nothing about what is actually cleaned, whether deletion is permanent, what auth is required, or what the result is. For a clearly destructive-sounding operation, this is a serious gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three words and not bloated, but its brevity reflects under-specification rather than efficient communication. There is no front-loaded purpose, scope, or consequence to justify the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No annotations, no output schema, and no parameter detail mean the description is the only information source, and it supplies none. An agent cannot safely invoke a data-cleaning operation on this basis.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema defines zero parameters, so there is nothing for the description to clarify; the baseline of 4 applies. No parameter meaning is lost because none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Clean monitor data' only restates the tool name with the underscore removed; it adds no scope, target, or effect detail. While 'clean' and 'monitor data' hint at a verb and resource, an agent learns nothing it could not infer from the identifier itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no mention of siblings such as get_monitor_data, get_monitor_setting, or update_monitor_setting. The description offers no condition or alternative that would help an agent choose this tool over its neighbors.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing. 'Clear' hints at an irreversible destructive action, but the description never states that contents are permanently removed, that the action cannot be undone, or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words with zero waste is front-loaded, but for a destructive, irreversible operation the definition is under-specified rather than concise. Brevity here removes information the agent needs instead of trimming noise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters, no annotations, and no output schema, the description is the only source of context, and it supplies none of the behavioral details (permanence, recoverability, required privileges) that matter for a clear/delete operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters (schema coverage 100% over an empty property set), so there is nothing for the description to clarify and the baseline of 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a verb ('clear') and a resource ('recycle bin'), so the basic operation is identifiable, but it is a near-verbatim restatement of the tool name and adds no scope detail. It does not distinguish this from siblings like list_recycle_bin, get_recycle_bin_status, or reduce_recycle_bin that operate on the same resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus the other recycle-bin siblings, nor any mention of prerequisites such as needing items present in the bin. The agent receives no routing guidance at all.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing: it does not say whether the action is reversible, whether the model remains loaded, whether it requires the connection to be idle, or what errors can occur. For a state-changing lifecycle operation with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no wasted words, and the verb is front-loaded. Its brevity is efficient, though it borders on under-specification rather than tight editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, an undocumented required parameter, and an unexplained XPack qualifier, the definition is not complete enough for an agent to invoke this lifecycle tool confidently. It needs at least the meaning of "name" and the effect of closing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the required "name" parameter is undocumented. The description never says whether "name" refers to the model name, a connection identifier, or an instance label, so the agent must guess from sibling naming conventions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb ("Close") and resource ("Ollama model connection"), which is more than a tautology. However, it does not clarify how "closing a connection" differs from sibling operations like delete_ollama_model or recreate_ollama_model, leaving ambiguity about whether the model is unloaded, disconnected, or disabled. The "(XPack)" tag hints at feature gating but is unexplained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus alternatives such as load_ollama_model, delete_ollama_model, or recreate_ollama_model. The agent must infer that this releases a live connection, but no prerequisites, sequencing, or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing about side effects (image creation), required permissions, or what happens to the running container. For a mutation tool with zero structured support, this is a complete gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are not concise but under-specified; there is no front-loaded information because there is essentially no information at all.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 3-parameter, fully-required mutation tool with no annotations, no output schema, and 0% parameter coverage is completely undocumented. An agent cannot reliably call this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all three required parameters (id, repo, tag). The description adds no meaning to any of them, leaving the agent to guess formats for the image repo name and tag.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Commit container' merely restates the tool name with no added specificity. It does not explain that this creates a new image from a container's current state, nor does it distinguish this from sibling image-creation tools like build_image or tag_image.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as build_image, save_image, or tag_image, nor any prerequisite information about the required container state.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, and it discloses nothing. It does not say whether an existing archive is overwritten (relevant to the 'replace' parameter), what 'secret' does (encryption/password?), where the archive is written, or whether the operation is blocking or async. For a 6-parameter mutation tool this is a complete gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The three-word description is short, but this is under-specification rather than conciseness; there is no wasted text because there is essentially no text. Nothing is front-loaded beyond the bare action, and critical constraints are omitted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, zero schema description coverage, no annotations, and no output schema, the definition is far too thin. An agent has no way to know required formats for 'type', the meaning of 'dst' vs 'name', or the behavior of 'secret' and 'replace'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all 6 parameters, and the description adds no meaning for any of them: 'dst', 'name', 'type', 'files', 'secret', and 'replace' are all left undefined. With four required parameters including an undocumented 'type' and 'dst', an agent cannot reliably construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Compress') and resource ('files/directories'), so the basic action is unambiguous. However, it provides no differentiation from the sibling decompress_file and no hint of what the compressed output is (archive format, destination, naming), even though three required parameters govern exactly that.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as decompress_file for the reverse direction. The agent is left to infer usage entirely from the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It says nothing about permissions required, whether the operation is destructive or resource-intensive, expected duration, or side effects. The description gives no behavioral insight at all.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short and front-loaded, but its brevity reflects under-specification rather than efficiency. It omits information an agent needs to call the tool correctly, so the two-word length is not a virtue.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a nested required object, no annotations, no output schema, and no parameter descriptions. The description is completely insufficient for an agent to understand what the nested 'backup' object should contain or what the tool will do. It fails to compensate for any of the missing structured context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter named 'backup', which is a nested object with 0% schema description coverage. The description does not explain what this object should contain or provide any example structure. With the schema doing no work and the description adding nothing, parameter semantics are entirely missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Create backup'), which distinguishes it from siblings like list_backups, restore_backup, and delete_backup. However, it adds no scope or qualifier beyond the tool name, so an agent cannot tell what kind of backup is created or how it differs from create_snapshot. It is minimally viable but vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, backup types, or how it relates to restore_backup/delete_backup/list_backups. The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden — and it discloses nothing. It does not say whether this requires credentials, what the different 'type' values imply, what happens if a duplicate name exists, or what the call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words is short, but this is under-specification rather than conciseness; there is no front-loaded actionable content beyond the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with three required parameters, an undocumented nested object, and zero annotation or output-schema support, the definition is completely inadequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 4 parameters, including a required nested 'vars' object and a required 'type' with no enumeration. The description adds no meaning to any of them, leaving the agent unable to construct a valid payload.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a verbatim restatement of the tool name with no additional information about what a 'backup account' is or what creating one entails. It is a tautology, not a clarification, and does nothing to separate it from siblings like create_backup or create_snapshot.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to create a backup account versus using update_backup_account, check_backup_account, or create_backup directly. The agent must infer the entire workflow from the sibling list alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Create SSL certificate' gives no information about permissions, whether the certificate is generated or uploaded, required preconditions, side effects, or what the cert object should contain. This is insufficient for a mutation tool with an opaque nested parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is structurally concise, but it is under-specified rather than appropriately concise. It is not front-loaded with useful information because it contains almost no substantive detail beyond restating the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations, no output schema, a nested object parameter with 0% schema description coverage, and several SSL-related sibling tools, the description is completely inadequate. It omits all contextual details an agent would need to invoke this tool correctly or choose it over alternatives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the single parameter 'cert' is a nested object with no properties documented in the schema. The description says nothing about what the cert object must include, what fields it accepts, or its expected shape. The description fails to compensate for the complete lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Create SSL certificate'. It is clear what the tool does, but it does not distinguish this tool from closely related siblings such as obtain_ssl, upload_ssl, or apply_ssl. An agent can understand the basic operation but may not know when to choose this over the alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, which sibling handles automatic issuance, or what situations call for manual certificate creation. The agent is left to infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It does not disclose permissions, side effects, validation rules, or what a created ClamAV config affects. It only restates the operation without any behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short and front-loaded, but it is under-specified rather than appropriately concise. It lacks the detail needed for a mutation tool with poorly documented parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a mutation tool with no annotations, no output schema, and 0% parameter description coverage, the description is completely inadequate. It omits required context about configuration format, path semantics, and return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, with three parameters (name, path, description) that are entirely undocumented. The description adds no meaning about what these parameters represent or how they are used.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Create ClamAV config'. It distinguishes itself from sibling verbs such as list, get, update, and delete. However, it does not clarify the scope or content of the config beyond the resource name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool instead of alternatives like update_clam_config or delete_clam_config. The create operation is implied only by the verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description carries the full burden of behavioral disclosure, and it provides none. It does not state whether creation requires elevated permissions, whether the compose is started immediately or left stopped, what happens on name conflict, or any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

At two words, this is not conciseness but under-specification. There is nothing to front-load because no meaningful information was written at all.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and zero parameter documentation for a mutation tool taking two required inputs, the description is entirely inadequate. An agent cannot reliably determine what the parameters should contain or what the call will produce.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both required parameters (name, content) have 0% schema description coverage and are completely undocumented in the description. There is no hint about content format (YAML?), size limits, or valid naming conventions, leaving the agent with no semantic guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Create compose" merely restates the tool name (create_compose) with no added detail. There is no indication of what a 'compose' is in this context, no mention of Docker Compose vs. anything else, and no differentiation from the many sibling create_* tools like create_container, create_website, or create_network.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance whatsoever on when to use this tool versus alternatives such as update_compose, start_compose, or the container-creation siblings. Nothing indicates prerequisites (e.g., a running Docker environment) or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, yet it says nothing about permissions, image/config requirements, side effects, or how the created container is returned. With a nested 'config' object as the only input, this is a severe gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short but this is under-specification rather than conciseness; there is no front-loaded useful content because there is no content at all.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a nested required config object, zero schema documentation, no annotations, and no output schema, the description is completely inadequate for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required parameter 'config' is an undocumented nested object. The description adds no information whatsoever about what 'config' must contain, leaving an agent unable to construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create container' is essentially the tool name restated with no additional detail. It conveys a verb and resource, but nothing that distinguishes it from the many sibling container operations (update_container, start_container, commit_container) or clarifies what kind of container is being created.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as create_compose, install_app, or build_image, and no prerequisites or context are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits, but it says nothing about permissions, side effects, scheduling behavior, or what 'job' entails. It provides no behavioral context beyond the verb 'Create'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two words, which is concise but severely under-specified rather than appropriately sized. It fails to convey any necessary information for invocation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a mutation tool with a nested object parameter, no annotations, and no output schema, the description is completely inadequate. It omits every detail an agent needs to call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter 'job' is a nested object with 0% schema description coverage, and the description does not mention it at all. The agent has no information about required fields, format, or syntax for the job object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create cronjob' merely restates the tool name without specifying scope, constraints, or how it differs from sibling tools like list_cronjobs or delete_cronjob. It identifies the verb and resource but adds no differentiating detail, matching the rubric's tautology level.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or alternatives are provided. The agent cannot tell when to prefer this tool over other creation tools or what conditions are required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure and delivers nothing. It does not say whether the operation is idempotent, what permissions are required, whether an existing database of the same name errors or is silently reused, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words is not conciseness but under-specification; the description is too sparse to be useful rather than economically worded. Nothing is front-loaded because there is nothing to front-load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-required-parameter creation tool with a nested object, no annotations, and no output schema, the description is completely inadequate. An agent has no basis to construct a correct call from it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two required parameters, one of which is an undescribed nested object ('db') and the other an unenumerated string ('type'). The description does not compensate at all, leaving an agent unable to know what 'type' values are valid or what shape 'db' must take.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create database' is a verbatim restatement of the tool name create_database, adding no information an agent doesn't already have from the name. It names a resource but offers no scope, no distinguishing detail from siblings like list_databases or delete_database, and no indication of what is being created.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus the many database-related siblings (list_databases, get_database, delete_database, mysql_* tools). No prerequisites, no exclusions, no alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden and delivers nothing. It does not state whether the operation is idempotent, whether it creates parent directories recursively, what happens if the path already exists, what permissions are required, or whether it is destructive to existing content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two words and technically terse, but this is under-specification rather than conciseness. Nothing is front-loaded because there is nothing to load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a filesystem mutation tool with no annotations, no output schema, and an undocumented required parameter, the definition is completely inadequate. An agent cannot safely call this without guessing at path semantics and error behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single 'path' parameter has only a type, no format or constraint info. The description adds nothing about whether the path is absolute or relative, whether it must be within an allowed root, or how nested paths are handled.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create directory' restates the tool name verbatim and adds no distinguishing scope, target, or effect. It is a bare verb+resource that an agent could infer from the name alone, with no differentiation from sibling tools like create_file or create_website.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool, no prerequisites, and no mention of alternatives such as create_file or save_file. The agent is left to infer that this is for creating a directory rather than a file.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates the resulting file is empty, but says nothing about overwrite behavior if the file already exists, permission requirements, error handling, or whether parent directories are created.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single terse phrase that is front-loaded but under-specified rather than efficient. It does not provide enough structure to guide correct invocation of the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is too incomplete. It leaves key behavioral questions (overwrite, permissions, error conditions) unanswered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no meaning for the sole 'path' parameter. While the parameter name is fairly self-evident, format expectations (absolute vs relative, allowed characters) are left entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Create') and resource ('file') and adds the qualifier 'empty,' which implicitly distinguishes it from save_file and other content-writing file tools. However, it does not name or contrast with any sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives like save_file, create_dir, or upload operations. It also omits prerequisites such as whether parent directories must exist or how path collisions are handled.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure for a mutation tool. It says nothing about required permissions, what the 'rule' object must contain, whether the rule takes effect immediately, or how conflicts with existing rules are handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The one-line description is short but under-specified rather than concise; there is no wasted wording, but also no information, so brevity here reflects a lack of content rather than efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A write tool with no annotations, no output schema, and an opaque nested object parameter needs substantial description to be callable correctly. Nothing here tells an agent what a valid rule payload looks like or what happens on success or failure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single parameter 'rule' is an undocumented nested object. The description adds no field names, structure, or examples, leaving the most important part of the call completely opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Create') and resource ('firewall rule'), so the basic action is unambiguous. However it merely restates the tool name and adds no scope, target system, or differentiation from the sibling 'delete_firewall_rule' and 'list_firewall_rules'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of related tools. An agent gets no help deciding between this and the sibling firewall operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears the full burden of behavioral disclosure, yet it only implies a mutation ('Create') without stating permissions required, whether the user is immediately active, how the path restricts access, or what happens on duplicate usernames. It conveys the bare minimum side-effect signal but no meaningful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single brief phrase, but it is under-specified rather than genuinely concise. Every word is front-loaded, yet the phrase fails to earn its place by adding any information beyond the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and four undocumented parameters, the description is completely inadequate. It omits usage context, parameter meaning, behavioral side effects, and return expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With four parameters and 0% schema description coverage, the description must compensate for the schema's silence, but it provides no information about userName, password, path, or description. An agent gets zero semantic guidance on any input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description pairs a specific verb ('Create') with a specific resource ('FTP user'), making the core operation unambiguous and readily distinguishable from siblings like update_ftp_user, delete_ftp_user, and list_ftp_users. However, it offers no explicit sibling differentiation or scope detail beyond the name itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no indication of required context. The description simply states the operation with no usage framing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, yet it says nothing about authentication requirements, what credentials (password vs privateKey) do, or side effects of creating a host.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The two-word description is not concise-but-complete; it is under-specified for a 9-parameter mutation tool. Brevity here reflects missing information rather than efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter creation tool with no annotations, no output schema, and 0% schema coverage, the description is completely inadequate; an agent cannot call it correctly from this text.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters, and the description adds no meaning for any of them -- nothing explains name vs addr, port defaults, authMode values, or the password/privateKey distinction.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description merely restates the tool name ("Create host") with no added scope, target system, or distinguishing detail from siblings like create_host_group, update_host, or create_container.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as create_host_group or test_host_connection. No prerequisites or context are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no permission requirements, no uniqueness constraint on the group name, no explanation of what isDefault triggers, and no indication of what happens to existing hosts or groups.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words is short, but this is under-specification rather than conciseness; there is no front-loaded content because there is essentially no content. Length is not the problem — missing information is.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% parameter coverage, the description is the only information channel and it delivers nothing. For a mutation tool that creates a persistent resource, this is wholly inadequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters. The description does not mention 'name' or 'isDefault' at all, so an agent gets no semantics for the required name field or the boolean default flag from either source.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create host group' simply restates the tool name create_host_group with no additional specificity. It conveys a verb and resource, but an agent learns nothing beyond what the identifier already says, and it is not distinguished from siblings like create_host, update_host_group, or list_host_groups.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as update_host_group or list_host_groups. The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses nothing: no idempotency behavior, no driver defaults, no error conditions, no side effects. For a mutation tool with zero annotation coverage this is a complete gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words is not conciseness but under-specification; there is nothing to front-load because no content exists. The score reflects brevity without substance rather than efficient communication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A two-parameter mutation tool with no annotations, no output schema, and no parameter documentation is entirely reliant on the description, which supplies nothing. An agent cannot call this correctly with confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no parameter meaning at all. "driver" is documented in neither place, and "name" gets no format, uniqueness, or constraint information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Create network" restates the tool name verbatim with no elaboration, scope, or differentiation. It is a tautology rather than a description: it does not say what kind of network, in what context (Docker networks given the sibling set), or what creating one entails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance and no reference to alternatives such as list_networks or remove_network. The agent must infer from the name alone that this is the creation counterpart to those siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral disclosure burden. It supplies none of the relevant traits for a creation tool: required permissions, what 'XPack' means, whether the model is pulled from a registry, what happens if the model already exists, or whether the operation is reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and brief, avoiding verbosity. However, '(XPack)' is an unexplained parenthetical that adds little for an agent, and the overall brevity comes at the cost of necessary guidance for a mutation tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and 0% parameter description coverage, the definition is too sparse. It does not explain prerequisites, the meaning of XPack, or how creation interacts with load_ollama_model and other Ollama siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter, 'name', with 0% schema description coverage. The description adds no meaning, format, uniqueness constraint, or source for that name. The resource name makes 'name' somewhat intuitive, but the description does not compensate for the missing schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb and resource ('Create Ollama model'), so the basic action is understandable. However, '(XPack)' is unexplained, and the description does not distinguish this tool from close siblings such as recreate_ollama_model, load_ollama_model, or sync_ollama_models. It largely echoes the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no alternatives are provided. With many Ollama-related sibling tools, the absence of routing guidance leaves the agent to infer when create_ollama_model is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses nothing. It does not say whether the snapshot is synchronous or long-running, what gets captured (files, databases, Docker images), whether it consumes significant disk space, or whether the operation is reversible. For a system-level mutation with zero annotation coverage this is inadequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single phrase is short but under-specified rather than concise; there is no front-loaded useful detail beyond the tool name itself. Length is not wasteful, but it conveys almost no information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter system mutation with no annotations and no output schema, the description is completely insufficient. An agent has no basis for understanding scope, side effects, parameter meaning, or how this differs from the many other snapshot tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Three parameters (name, withDocker, description) exist with 0% schema description coverage, and the description offers no information about any of them. In particular 'withDocker' and 'description' are entirely undefined, and the description does not compensate for the schema's silence as required at low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Create system snapshot'), so an agent can tell what operation is being performed. It does not distinguish this from adjacent snapshot siblings such as recreate_snapshot, import_snapshot, or load_snapshot, which affects whether the agent picks the right one. Clear but undifferentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like recreate_snapshot or import_snapshot, nor any stated prerequisites (permissions, disk space, running tasks). The sibling list is dense with snapshot-related operations, so the absence of routing guidance is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about mutation effects, required permissions, side effects, or whether the operation is reversible, leaving the agent with no behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are concise but severely under-specified for a tool that needs behavioral context. There is no structure or front-loading of useful information, so brevity here harms rather than helps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and zero schema description coverage, the description is completely inadequate for a mutation tool. It leaves the agent unable to call the tool correctly without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, name, is undocumented in both the schema (0% description coverage) and the description. The description adds no meaning about format, constraints, or examples beyond the bare parameter name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the verb and resource ('Create volume'), but adds no scope or distinguishing detail beyond the tool name. It is clear but essentially restates the name create_volume, leaving purpose at minimum viable with clear gaps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indication of when to use this tool, what prerequisites exist, or how it relates to siblings like list_volumes or remove_volume. Provides no usage guidance whatsoever.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It says nothing about permissions, side effects, reversibility, required configuration, or what happens on success or failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two words, but this is under-specification rather than useful conciseness. It does not front-load actionable context because there is none.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a website creation tool with a required nested object, no annotations, no output schema, and zero parameter documentation, the description is completely inadequate. It omits every detail an agent would need to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter, 'site', which is a nested object with 0% schema description coverage. The description adds no information about what this object should contain or how it should be structured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Create website' merely restates the tool name and gives no specific scope, required inputs, or distinguishing detail beyond the verb 'create'. It is a tautological restatement rather than a useful purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as update_website, delete_website, or list_websites. The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description must carry the behavioral burden. 'Add' implies a mutation, but the description omits side effects, authentication/permission needs, domain validation behavior, and conflict handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a four-word fragment with no wasted words and the action front-loaded. It is arguably too terse for a three-parameter mutation tool, but it is structurally not bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% schema description coverage, the description is far too sparse to support correct invocation. It leaves parameter usage and mutation behavior unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description should compensate. It conceptually references 'domain' and 'website' but ignores the port parameter entirely and adds no format, constraint, or identifier semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Add') and resource ('domain to website'), making the core action clear. However, it does not differentiate this create/attach operation from siblings such as update_website_domain or delete_website_domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or alternatives are provided. The agent must infer that this is for adding a domain rather than updating, listing, or deleting one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden but discloses almost nothing. It does not state whether existing files at 'dst' are overwritten, where extraction lands, what permissions result, or that 'secret' is a password for encrypted archives - all critical for a filesystem-mutating operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are technically concise, but this is under-specification rather than efficient brevity. Nothing is front-loaded because there is essentially no content to structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with three required undocumented parameters, no annotations, and no output schema, the description is completely inadequate. An agent lacks the information needed to call it correctly or safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and four parameters are undocumented in the schema. The description adds no meaning for any of them: 'path', 'dst', 'type' (apparently the archive format), and 'secret' (likely a password) are left entirely for the agent to guess.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Decompress') and resource ('archive'), so the basic operation is identifiable. However, it does not distinguish this from the inverse sibling compress_files or indicate what archive formats are supported, leaving the scope vague.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like compress_files, nor any prerequisites such as whether the destination must exist or be empty. The agent must infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavior, and it discloses nothing. It does not state that the operation is destructive/irreversible, whether the backup file is permanently removed or moved to the recycle bin, or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words with no waste, but this is under-specification rather than conciseness. There is no structure or front-loaded content because there is no content at all.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an irreversible mutation tool with no annotations, no output schema, and an undocumented required parameter, the description is completely inadequate. Nothing an agent needs to invoke it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single required parameter 'id' has 0% schema description coverage and the description adds no meaning whatsoever about what the id identifies (backup record, account, snapshot). An agent cannot tell from either source what value to supply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description merely restates the tool name verbatim as 'Delete backup'. It gives no scope, no distinction from siblings such as list_backups, create_backup, restore_backup, or delete_backup_account, and no indication of what a backup record is versus a backup account.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to delete a backup, whether it is reversible, or when to prefer an alternative. The name implies a delete operation on a backup, but nothing in the text tells an agent how to choose this tool over its siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about irreversibility, required permissions, whether associated backup files are removed, or any confirmation/undo path for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four words with no structure. It is short, but this is under-specification rather than conciseness — there is no front-loaded detail or actionable content to earn brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, unannotated tool with two undocumented parameters and no output schema, the description is wholly inadequate. An agent cannot safely invoke it from this definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Two parameters with 0% schema description coverage, and the description explains neither. The required 'type' parameter and the 'name' parameter are completely undocumented, so an agent has no way to know valid values or whether name is ignored/required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Delete backup account'), which is enough to know the operation, but it is essentially a restatement of the tool name and gives zero differentiation from siblings like update_backup_account, create_backup_account, or delete_backup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as delete_backup or list_backup_accounts. The agent must infer all routing from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. "Delete" implies a destructive, likely irreversible operation, but nothing is said about whether the certificate is revoked, what happens to websites bound to it, or what permission is required — a significant gap for a deletion tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The three-word phrase is front-loaded and free of waste, but it is under-specified rather than concise — it omits any information an agent would need beyond the tool name, so brevity comes at the cost of usefulness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation operation with no annotations, no output schema, and an undocumented required parameter, the description is too thin. An agent cannot determine deletion consequences or the meaning of 'id' from the definition alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single required parameter 'id' has 0% schema description coverage, and the description does not explain what the id refers to or where to obtain it (presumably list_certificates). With one undocumented parameter, the description fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Delete SSL certificate"), which is enough to distinguish it from the many sibling certificate tools such as list_certificates, get_certificate, create_certificate, obtain_ssl and renew_ssl. However, it adds no scope detail (which certificate, by what identifier) that would fully separate it from them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like renew_ssl, resolve_ssl or upload_ssl, nor any stated prerequisite (e.g., the certificate must not be in use by a site). Usage must be inferred from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Delete' implies destruction, but the description never states whether the config is recoverable, whether it is currently in use by active scans, or what permission is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four words with zero padding and the object of the action front-loaded, so nothing is wasted. However, the brevity reflects under-specification rather than efficiency for a destructive operation of this complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A destructive, mutation-class tool with no annotations, no output schema, and 0% parameter documentation has only a four-word description to work with. Nothing about irreversibility, side effects, or identifier sourcing is conveyed, leaving the agent materially under-informed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required 'id' parameter is a bare number with no meaning attached anywhere. The description does not say whether this is the config ID, name, or index, nor how to obtain valid values (e.g., from list_clam_configs).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete ClamAV config'), which cleanly distinguishes it from the sibling create_clam_config, update_clam_config, and list_clam_configs. It stops short of explicitly routing to those siblings, but the CRUD verb makes the distinction obvious.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus update_clam_config or create_clam_config, no prerequisites, and no warning about when deletion is inappropriate or irreversible. The agent must infer all of this from the verb alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing. It does not state that the deletion is destructive/irreversible, whether confirmation or elevated permissions are required, or what happens to a running cronjob.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a two-word phrase with no waste, but this is under-specification rather than effective conciseness. There is nothing front-loaded because there is essentially nothing to front-load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation with no annotations, no output schema, and an undocumented required parameter, the description is completely inadequate. An agent cannot determine irreversibility, target semantics, or expected outcome from this definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema documents nothing about the single required `id` parameter. The description does not mention it at all, leaving ambiguous whether it is a numeric job ID, name, or index, so no meaning is added beyond the raw type.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Delete cronjob" states a specific verb (delete) and resource (cronjob), so the basic operation is identifiable. However, it adds nothing beyond the tool name itself and does not distinguish this from siblings like list_cronjobs or create_cronjob, nor clarify scope (single job by ID vs bulk).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this versus the sibling cronjob tools, no prerequisites (e.g., does the job need to be stopped first?), and no exclusions. The agent is left to infer everything from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. For a destructive database operation, it says nothing about permanence, data loss, required permissions, dependencies, reversibility, or expected response. This is a critical gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two words long. While brief, it is under-specified rather than appropriately concise; it lacks the structure and detail needed for a destructive operation. The brevity fails to earn its place as a useful definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that this is a destructive operation with no annotations, no output schema, and no parameter documentation, the description is completely inadequate. An agent cannot safely infer correct usage or consequences from it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has two required parameters, id and type, with 0% description coverage. The description adds no meaning about what id identifies, what type values are valid, or how they relate to database deletion. With low schema coverage, the description must compensate and does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete database' exactly restates the tool name with no additional specificity. It gives the verb and resource at the most literal level but does not distinguish the operation from any sibling delete tool in the environment. This fits the tautology calibration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as list_databases, get_database, or create_database. No prerequisites, no when-not-to-use conditions, and no mention of alternatives are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It conveys a destructive operation but omits irreversibility, permission requirements, forceDelete semantics, and whether deletion goes to a recycle bin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The phrase is concise, front-loaded, and free of filler. However, it is too terse for a destructive tool with an undocumented forceDelete parameter, leaving necessary structure and safety context unstated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, 0% schema description coverage, and two parameters, the description is far too sparse. It does not explain parameter behavior or destructive consequences, making it inadequate for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters. The description does not explain the path format or the optional forceDelete boolean, so it fails to compensate for the missing schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete file or directory'), distinguishing it from siblings like delete_website, delete_database, and delete_backup. However, it adds no scope or context about the target filesystem or alternatives such as recycle-bin operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no exclusions, and no alternative tools named. The description implies deletion is the purpose but does not say when to prefer this over moving, renaming, or other file operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing beyond the mutation verb. It does not say whether the deletion is irreversible, whether a confirmation or force flag exists, what permissions are required, or what happens to rules that reference this one.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with zero padding, so there is no wasted text and the operation is front-loaded. But it is under-specified rather than genuinely concise, delivering no information beyond the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive operation with no annotations, no output schema, and 0% parameter coverage, the description is far too thin. An agent has no basis for knowing the id format, the irreversibility of the action, or how the call relates to its sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single parameter 'id' is undocumented in both schema and description. The description does not say whether id is the numeric rule ID, how to obtain it, or whether it refers to a list index versus a database identifier.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb and resource ('Delete' + 'firewall rule'), so an agent knows the general operation. However, it is essentially a restatement of the tool name and does nothing to distinguish it from siblings like create_firewall_rule or list_firewall_rules beyond what the name already conveys.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisite conditions, and no reference to alternatives such as list_firewall_rules (to find the id) or create_firewall_rule. The agent gets no routing help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. For a destructive, likely irreversible operation it says nothing about confirmation requirements, permission scope, or side effects such as removing home directories or active sessions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The phrase is front-loaded and free of padding, but at three words it is under-specified rather than genuinely concise. Brevity here comes at the cost of all operational detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one required parameter, no output schema, and no annotations, the definition is too thin for a destructive mutation tool. Nothing tells the agent how deletion is confirmed, what happens to the account's data, or what a successful result looks like.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single 'id' parameter is undocumented, so the description must compensate. It does not clarify whether 'id' is the FTP account ID or username, nor whether it can be obtained from list_ftp_users.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (Delete) and resource (FTP user), so an agent knows exactly what it does at a glance. It offers no differentiation from close siblings such as update_ftp_user or operate_ftp, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisite (e.g. whether the account must be disabled first), and no mention of alternatives such as update_ftp_user or operate_ftp. The agent must infer usage purely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden and fails: it does not state whether the delete is permanent, whether associated groups/SSH keys/backups are cascaded, whether confirmation or elevated permissions are required, or whether the host is merely detached. Only the base implication of the verb 'delete' is conveyed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are technically concise but reflect under-specification rather than economy. There is no front-loaded detail to compress because no substantive information was written.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A destructive, irreversible operation with no annotations, no output schema, an undocumented required parameter, and an enormous sibling set — none of the missing context is supplied. This is inadequate for an agent to invoke the tool safely and correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required parameter 'id' is undocumented in both schema and description. The description does not clarify whether the id is a host record id, an internal group id, or an external identifier, so it adds nothing beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The text 'Delete host' restates the tool name verbatim with no added scope, target type, or outcome. Among siblings such as delete_host_group, delete_website_domain, and remove_container, an agent gets no help telling this apart from near-identical delete tools beyond the name itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, prerequisites, or alternatives are given. There is no hint about which host lifecycle stage this applies to or what to do instead when a host merely needs to be disabled vs. removed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden and it does not meet it. "Delete" signals a destructive operation, but nothing states irreversibility, whether nested hosts are affected, or permission requirements. For a deletion tool this is a meaningful gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words with zero waste and front-loaded verb, but the brevity comes at the cost of under-specification rather than tightness. It is short without being informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations, no output schema, and an undocumented required parameter, the description omits everything an agent needs beyond the name: target semantics, side effects, and outcome. Inadequate for the operation's risk profile.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single parameter is documented only as a bare number. The description says nothing about whether "id" is the host group identifier or a host identifier, nor about valid values, so it fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Delete host group" gives a specific verb and resource, so the action is unambiguous on its own. However, it is essentially a restatement of the tool name and adds nothing to distinguish it from nearby siblings such as update_host_group_by_id or list_host_groups. Minimum viable clarity rather than genuinely differentiating.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (e.g. group must exist or be empty), and no pointer to alternatives such as update_host_group or update_host_group_by_id. The agent is left to infer everything from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full behavioral burden, and it discloses nothing. It does not say whether the deletion is irreversible, what happens to hosts still relying on the key, whether confirmation or elevated permissions are required, or whether any cleanup occurs. 'Delete' is already implied by the tool name, so no new information is added.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a four-word fragment with zero waste and nothing to trim. But its brevity comes from under-specification rather than discipline, so it is merely minimal, not well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation tool with no annotations, no output schema, and an undocumented required parameter, the definition supplies none of the context an agent needs. It is the same string as the tool name and nothing more.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single parameter 'id' is typed only as number, so the description must compensate and does not. Critically, it is ambiguous whether 'id' refers to the SSH key record or the host, which directly affects correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete host SSH key'), so the operation is unambiguous in isolation. However, it does nothing to distinguish itself from the four closely named siblings generate_host_ssh_key, get_host_ssh_key, sync_host_ssh_key and update_host_ssh_key.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, no mention of alternatives. The agent must infer from the name alone that this is the removal counterpart to the other *_host_ssh_key tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It identifies a destructive action but says nothing about irreversibility, required permissions, or side effects such as whether the model must be unloaded first.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded phrase with no filler, which is appropriately concise. It is arguably too terse for completeness, but conciseness itself is strong.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive one-parameter tool with no annotations and no output schema, the description is too thin. It omits the required ids parameter and any operational context needed to invoke it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one required parameter ('ids') with 0% description coverage, and the description never mentions it. It adds no format, source, or selection meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Delete) and resource (Ollama model), with a parenthetical XPack edition hint. It does not differentiate from close_ollama_model or explain scope, so it is clear but not fully sibling-aware.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is given, and alternatives such as close_ollama_model are not mentioned. The name implies deletion, but explicit usage guidance is absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure for a destructive operation, and it says nothing about irreversibility, required permissions, batch behavior of the ids array, or interaction with the recycle bin. It only implies mutation via the verb 'Delete'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single phrase is front-loaded and waste-free, but its brevity stems from under-specification rather than disciplined editing. It is appropriately sized only in the sense that there is almost nothing to say.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations, no output schema, and one undocumented required parameter, the description is far too thin. An agent gets no confirmation of what happens after deletion or how to obtain valid snapshot IDs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema documents only types; the description adds nothing about the required 'ids' array (format, whether multiple snapshots can be deleted at once, or ID source). It also describes a singular 'snapshot' while the parameter is a plural array, adding ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Delete ... snapshot'), so the agent knows the operation is a removal of snapshots. It does not, however, distinguish this from adjacent siblings such as recover_snapshot, recreate_snapshot, or load_snapshot, nor does it clarify the 'system snapshot' concept.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no warning about when deletion is inappropriate, and no pointer to alternatives like recover_snapshot or the recycle bin. The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not the destructive/irreversible nature, not whether associated files, databases, or SSL certificates are removed, not permission requirements, and not whether the action can be undone or recovered from the recycle bin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are not conciseness here but under-specification; there is nothing to be front-loaded because no substantive content exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A destructive, unannotated mutation tool with an undocumented ID parameter and no output schema still leaves the description completely inadequate — an agent cannot safely invoke this tool on the basis of the provided information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single required parameter 'id' has 0% schema description coverage (bare number type), and the description adds no meaning — it does not say whether this is a website ID or domain ID, nor where the agent should obtain a valid value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Delete website" merely restates the tool name with no additional specificity — no indication of scope (does it remove the domain binding, files, database, SSL cert, nginx config?). It also does not distinguish itself from siblings such as update_website or uninstall_app, which could plausibly be confused with it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives or consequences. An agent gets no signal about when deletion is appropriate versus when update_website or another destructive sibling should be used instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It says only 'Remove domain from website', omitting whether the action is permanent, what permissions are required, and side effects on SSL/DNS. It conveys a destructive action but no operational details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. However, its extreme brevity may be under-specification rather than effective conciseness for a destructive tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a destructive operation with no annotations, no output schema, and an undocumented parameter, the description is too sparse. It omits parameter meaning, safety profile, and expected behavior, leaving significant gaps for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single 'id' parameter has no description. The description does not clarify whether 'id' refers to the website domain ID, the website ID, or a domain name, so it fails to compensate for the missing schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb 'Remove' and resource 'domain from website', making the action clear. It does not name sibling tools like delete_website or update_website_domain, so an agent must infer that this targets only the domain association, not the whole site.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus delete_website, create_website_domain, or update_website_domain. The description offers no prerequisites or context, leaving the agent to infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not whether the link is temporary or permanent, whether it requires authentication, whether it expires, or whether it is safe/repeatable. Three words cannot cover a link-generation operation with zero structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three words are short, but this is under-specification rather than conciseness. Front-loading is irrelevant when there is essentially nothing to front-load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No annotations, no output schema, and no parameter documentation leave the agent with nothing to work from beyond a two-word purpose. For a tool in a large file-management family, this is inadequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required parameter 'path' is never referenced in the description. With a required, entirely undocumented parameter, the description fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The phrase 'Get download link' names a verb and an artifact, so an agent can guess it produces a URL for a file. But it never mentions the file it operates on and gives no basis for distinguishing it from siblings like get_file_content, list_files, or check_file. Vague but not misleading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives despite ~180 sibling tools including several that also surface file contents. The agent must infer the workflow entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses nothing: no permissions required, no statement that this is an arbitrary-command mutation, no mention of sandboxing, timeouts, or side effects. For a raw command executor this is a critical omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are not concise but under-specified; nothing is front-loaded because there is nothing to load. It wastes no words only because it has almost none.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that runs arbitrary commands, with no annotations, no output schema, and undocumented parameters, the description is wholly inadequate. An agent cannot determine execution context, safety profile, or return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters (command, cwd) have 0% schema description coverage, and the description adds no meaning for either — it does not explain that command is a shell string or that cwd sets the working directory. The description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Execute command" restates the tool name exec_command almost verbatim, making it a tautology rather than a description of purpose. It does at least signal a shell/command execution capability, but it gives no indication of scope, target environment, or how it differs from any sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance at all on when to use this tool, what it operates against, or what alternatives exist. With dozens of sibling tools covering files, containers, and services, the agent has nothing to route on.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the entire behavioral burden, yet it discloses nothing. It does not say whether generation overwrites an existing key, whether the key is applied immediately, whether elevated permissions are needed, or whether the operation is destructive/reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short, front-loaded phrase with no filler, which is structurally efficient. But it is a bare fragment rather than a sentence, so its brevity comes from under-specification rather than tight editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, an undocumented required parameter, and several ambiguous siblings, the description should clarify scope, side effects, and return behavior. None of that is present, so an agent cannot call this tool confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the single required 'id' parameter, and the description adds no clarification (host id? key id? numeric identifier for what?). The word 'host' hints weakly at the domain, but the parameter remains effectively undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (Generate) and resource (host SSH key), which is clear enough as a standalone statement. However it does nothing to distinguish this tool from its many close siblings (get_host_ssh_key, update_host_ssh_key, sync_host_ssh_key, delete_host_ssh_key), leaving the agent to infer the difference from names alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of prerequisites (e.g., an existing host record), and no routing to alternatives such as sync_host_ssh_key or update_host_ssh_key. The agent must guess both the context and the correct sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It adds nothing beyond the word 'Get' and does not disclose permissions, response shape, or any operational constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The phrase is short, but it is under-specified rather than concise. It offers no structure or additional information to justify its brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with an undocumented required parameter and no output schema, the description is completely inadequate. It leaves the agent unable to call the tool correctly without guessing clientType values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage for the required clientType parameter. The description does not explain what clientType means, what values it accepts, or how it affects the result.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name almost verbatim: 'Get backup account client info.' It does not specify what 'client info' contains or distinguish this tool from siblings like get_backup_account_options or list_backup_accounts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool, what prerequisites exist, or which sibling tools it complements. The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, and it discloses nothing — not what 'options' are (e.g. provider types, storage regions, credential schemes), nor whether the call is a safe read. The zero-parameter shape reduces the surface somewhat, but the meaning of the returned 'options' is completely opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short sentence, so there is no padding or buried information. However, brevity here stems from under-specification rather than tight editing, leaving the one line with almost no informational payload.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotation coverage, so the description is the only source of information about what this tool returns — and it says nothing. An agent cannot know what a 'backup account option' is, which makes the definition unusable for correct invocation in a crowded backup-management sibling set.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so per the baseline rule this dimension defaults to 4. There is no parameter ambiguity to resolve and no schema detail the description fails to supplement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a near-verbatim restatement of the tool name ('Get backup account options' for get_backup_account_options), adding no verb, resource scope, or differentiation. With siblings like list_backup_accounts, get_backup_account_client_info, and check_backup_account, an agent cannot tell what distinguishes this call.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of alternatives such as list_backup_accounts or get_backup_account_client_info, and no prerequisites. The agent is left to guess entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, yet it says nothing beyond the implied read nature of 'get'. It does not disclose permissions required, what certificate details are returned, or how a missing/invalid certificate is handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, which is structurally efficient. The terseness, however, shades into under-specification rather than genuinely earned conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a lookup tool with no annotations, no output schema, and an undocumented parameter, the description is too thin. It leaves the agent without the identity of the parameter or the nature of the returned details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required 'id' parameter is undocumented. The description never explains that the ID identifies a certificate or its expected format/type, so it fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Get SSL certificate details'), which is clear enough to distinguish a single-certificate lookup from list_certificates. However, it does not differentiate itself from closely related siblings like get_website_ssl or list_certificates, so an agent still has to infer which certificate tool fits.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as list_certificates, get_website_ssl, or obtain_ssl. No prerequisites, context, or exclusions are given, leaving the routing decision entirely to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, and it discloses nothing: not whether this is a read-only lookup, not what fields are returned, not whether it requires ClamAV to be installed or running. For a zero-parameter info getter this is a real gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four words, front-loaded, zero waste or filler. It is not bloated, though its brevity is under-specification rather than genuine economy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, no annotations, and a bare description, an agent has no way to know what this call returns or when it is the right call. The description should at minimum name the returned information (e.g., engine/definition versions and status) and disambiguate it from the other ClamAV tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so per the rubric the baseline is 4; there are no parameter semantics for the description to add or omit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.