Nautical miles to kilometers

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. It does state 'No browser is launched,' which is a useful safety note, but it fails to disclose what happens with the many other parameters (e.g., whether city or json are validated, what 'discarded after the shape check' means), what the return value is, or any side effects or error conditions. The description is largely silent on behavior beyond that one clause.

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, concise sentence, which is structurally efficient. However, it is under-specified for the tool's complexity: with 9 optional parameters and no annotation or output schema, one sentence is not appropriately sized. The conciseness is good, but the content is inadequate, so a middle score is appropriate.

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 9 parameters, zero annotations, and no output schema, the description is completely inadequate. It does not explain what the tool does with the variety of inputs (city, json, path, zone, query), how they relate to 'checking a URL,' or what the result looks like. An agent cannot reasonably call this tool correctly based solely on the description and 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?

Schema description coverage is 100%, so the baseline is 3. The tool description adds no meaning beyond what the schema already provides; each parameter has a description in the schema, but those descriptions are cryptic (e.g., 'discarded after the shape check') and the tool description does not clarify their semantics or relationship to the stated purpose. Thus no bonus is warranted, and the baseline holds.

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 and resource ('Check whether a URL can be opened'), but the input schema accepts many non-URL parameters (city, feed, json, path, zone, query) with no explanation, making the stated purpose misleading. It also fails to differentiate from sibling tools like playwright-url-ok, normalize-url, or fetch-status, so an agent cannot reliably select 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 guidance is provided on when to use this tool versus alternatives. The description does not mention any exclusion criteria or context that would help an agent decide between this and siblings like web-fetch or playwright-url-ok. There is no implied usage beyond the one-sentence purpose, and no 'when not to use' statement.

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 only states 'Expression discarded,' which is ambiguous—does it mean the result is discarded, or the input is discarded? It does not disclose return behavior, side effects, or safety profile. Minimal and unclear.

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 concise (two short sentences), but the second sentence is ambiguous and the entire content is under-specified. It is not well-structured because it omits essential information while including a vague behavioral note.

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 9 parameters, no output schema, and no annotations, the description is completely inadequate. It does not explain what the tool returns, how parameters relate to the stated purpose, or any side effects. An agent would have no idea how to 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 coverage is 100%, but the description adds no meaning to any parameter. It does not mention how the arithmetic expression maps to any of the 9 parameters (ref, url, city, feed, host, json, path, zone, query), which are unrelated to arithmetic. The description actually contradicts the schema, creating confusion rather than adding 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?

The description states a specific verb and resource ('Evaluate a+b style arithmetic'), which is not a tautology. However, it is vague about how the expression is provided, and the input schema contains no arithmetic-related fields (all parameters are URLs, file paths, etc.), making the stated purpose misleading and unclear in practice.

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 zero guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or sibling tools, leaving the agent without any basis for selection.

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 provided, so the description carries the burden. It discloses that page content is not stored, but it omits the fact that most input parameters are discarded after shape checks, and it doesn't describe the actual behavior for non-URL inputs. The description's narrow claim conflicts with the schema's broader scope.

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 sentences and concise, but it is misleadingly narrow. It front-loads a specific behavior that is not the whole picture, and it doesn't structure the information to reflect the tool's actual 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?

With 9 optional parameters, no output schema, and no annotation context, the description is woefully incomplete. An agent cannot know what to expect for other inputs, what the return format is, or how this relates to sibling tools. It only covers a single URL case.

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 100%, so baseline is 3, but the description adds no parameter-level meaning. It only mentions URL behavior, leaving the other 8 parameters unexplained. The description fails to clarify which parameters are relevant for the stated purpose and how they interact.

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 function ('Return host, scheme, and HTTP status for a URL') but the input schema reveals a much broader set of validation behaviors (city, feed, JSON, etc.) not mentioned. This misrepresents the tool's scope and fails to distinguish it from siblings like fetch-status or normalize-url.

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 on when to use this tool vs alternatives like fetch-status or normalize-url. The description doesn't mention any conditions or exclusions.

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. It only promises 'No identifiers are retained,' which is a privacy note, but it doesn't clarify whether the tool performs network calls, reads files, or has any side effects. The phrase 'discarded after the shape check' in the schema hints at read-only behavior, but the description itself is silent on mutation, permissions, or output behavior.

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 short sentences with no filler. The core purpose is stated first, and the privacy guarantee is a valuable addition. It is efficiently front-loaded and easy to parse, though it could afford a bit more substance.

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 tool's complexity (9 heterogeneous parameters, no annotations, no output schema), the description is insufficient. It doesn't explain what 'classification' means, what the output looks like, or when an agent should prefer this over a more specific sibling. The schema param descriptions give hints, but the overall behavior and return format are missing, making the tool hard to use 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?

The input schema has 100% coverage, with each parameter described individually (e.g., 'Git ref name; discarded after the shape check', 'JSON text to validate; discarded after the check'). The tool description adds no additional parameter semantics, so the baseline of 3 applies—the schema already does the heavy lifting.

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 verb ('Show') and a resource ('this request classified'), but 'classified' is ambiguous—it doesn't specify what classification criteria or categories are involved. It also doesn't distinguish the tool from sibling shape-checkers like 'domain-shape' or 'github-repo-shape', leaving the agent to infer the tool's unique role.

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 given on when to use this tool versus the many sibling tools that also inspect inputs (e.g., 'normalize-url', 'validate-json', 'file-path-ok'). There are no conditions, exclusions, or alternatives mentioned, so the agent cannot route correctly.

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 burden. It only mentions 'without WHOIS or ownership data', which hints at a non-network operation but does not disclose side effects (likely none), data handling, or behavior for the other parameter types. The schema notes 'discarded' for some fields, but that is in structured data, not the description.

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 concise sentence, but it is incomplete and under-specified for a tool with 9 heterogeneous parameters. Conciseness alone is not effective when it omits essential scope 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?

With 9 optional parameters and no output schema, the description provides almost no context. It does not explain what the tool returns, how each parameter is processed, or why it exists alongside similar shape-checking tools. An agent would be unable to use it correctly without opening the schema and inferring intent.

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 100%, giving baseline 3, but the description does not add meaning beyond the schema and actually conflicts by only referencing hostname. The description fails to explain how the other parameters map to the tool's behavior, so it does not compensate for the schema's terse per-field notes.

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 action for hostnames ('Split a hostname into labels') but the input schema accepts 9 unrelated parameters (ref, url, city, feed, host, json, path, zone, query), many of which are discarded after checks. The description does not represent the tool's actual scope, making it misleading for an agent deciding what this tool does.

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 on when to use this tool versus the many shape-specific siblings (github-repo-shape, jira-key-shape, figma-url-shape, etc.). The description gives no conditions, exclusions, or alternatives, so an agent cannot route correctly.

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 behavior. It indicates a network HEAD request and a status-only return, but omits any side effects (e.g., that it makes an external call), potential timeouts, or what 'status' means (HTTP status code?). It also does not clarify the role of the many unrelated parameters, creating ambiguity about the actual behavior.

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 filler, which is good for conciseness. However, it is too brief given the tool's broad parameter set and lacks the necessary structure to clarify the tool's full scope.

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 9 parameters, no output schema, and no annotations, the description is insufficient. It does not describe what happens with non-URL parameters, the format of the returned status, error handling, or any preconditions. An agent would not know how to correctly invoke this tool beyond the simplest URL case.

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?

Although the schema provides 100% coverage of parameter descriptions, the tool description itself adds no value to parameter understanding. More critically, the description ('HEAD a public URL') conflicts with the presence of parameters like city, timezone, query, and json, suggesting either a mismatch in the tool's scope or missing context. The description does not explain how these parameters relate to the stated purpose.

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 action (HEAD) on a resource (public URL) and the return type (status only). This is clear and distinct from more comprehensive tools like web-fetch or playwright-url-ok, though it does not explicitly name those 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?

No guidance is provided on when to use this tool versus siblings like browser-url-ok, normalize-url, or web-fetch. The description does not mention scenarios, exclusions, or prerequisites, leaving the agent to infer based solely on 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 must disclose all behavioral traits. It only states 'Path discarded' and implies parsing, but does not mention whether the tool mutates anything, what it returns, or how it handles the other 8 parameters. For a tool that likely validates shapes (read-only), this is a significant gap; the agent cannot anticipate side effects or output structure.

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 concise (one sentence) and front-loads the core action. However, it omits essential context about the parameter set and fails to explain why the schema contains unrelated fields. It is under-specified rather than effectively concise, so it earns a mid score.

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 complexity (9 parameters, no annotations, no output schema), the description is far from complete. It does not clarify how the tool processes or discards the various inputs, what the expected output is, or how it relates to the sibling shape tools. An agent cannot reliably call this tool correctly based on the current description.

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 provides descriptions for all 9 parameters (100% coverage), so the schema does the heavy lifting. However, the tool description does not reference any parameters or explain how they relate to the Figma URL parsing purpose. The schema descriptions themselves are generic ('City name for a public weather hint') and seem unrelated to Figma, which is confusing. The description adds no semantic value beyond the schema, so baseline 3 is appropriate.

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 ('Parse') and resource ('Figma file URL') and notes a behavior ('Path discarded'), which gives some clarity. However, the input schema contains 9 unrelated parameters (city, feed, json, etc.) with no mention in the description, making it ambiguous whether this tool handles those inputs or is solely for Figma URLs. It does distinguish from siblings like 'domain-shape' and 'github-repo-shape' by name, but the mismatch between description and schema clouds the purpose.

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 the many sibling shape/URL tools. It does not state what input types are accepted (only a Figma URL?) or what happens when other parameters are passed. There are no exclusions or alternative recommendations, so an agent cannot infer the appropriate usage 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?

The description discloses 'No disk access,' which is a useful safety trait, but it does not explain what 'safe' means (e.g., traversal checks, absolute paths) or what happens on invalid input. It also omits that the tool accepts many other parameter types, potentially misleading an agent into thinking only paths are handled. With no annotations, the description carries the full behavioral burden and falls short.

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 brief and waste-free, stating the core action and a safety caveat in two short sentences. It does not over-elaborate, which is good for conciseness, though the brevity contributes to incompleteness in other dimensions.

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 tool's complexity (9 parameters, no output schema, no annotations), the description is severely incomplete. It fails to define 'safe,' explain the role of the non-path parameters, or indicate return behavior. An agent would be uncertain about valid inputs and expected 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?

Schema coverage is 100%, so each parameter already has a description, meeting the baseline. The tool description adds no extra meaning beyond the schema, such as how parameters relate or whether they are alternative inputs. It simply repeats the schema's intent without clarifying the overall function.

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 and resource ('Check whether a path looks safe') and notes no disk access, which distinguishes it from disk-touching tools. However, it does not differentiate from sibling shape-checkers like browser-url-ok or figma-url-shape, and the schema's 9 parameters (ref, url, city, feed, host, json, zone, query) are entirely unexplained, muddying the actual scope.

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 given for when to use this tool over alternatives. With siblings like browser-url-ok, github-repo-shape, and validate-json, an agent cannot tell which shape checker to pick. The description also fails to clarify whether the non-path parameters are supported or intended for other uses.

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 full responsibility. It only says 'parse owner and repo' but doesn't disclose what happens with invalid URLs, whether it accesses the network, whether it's read-only, or what the return structure is. The schema includes many unrelated parameters, and the description doesn't explain their role, leaving behavioral expectations unclear.

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 concise but not appropriately sized for a tool with 9 parameters and no output schema. It lacks necessary structure—no front-loaded usage hints, no parameter highlights, and no exclusions. It is under-specified rather than efficient.

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 complexity (9 optional params, no annotations, no output schema), the description is grossly incomplete. It doesn't specify the expected input format, behavior on failure, the exact output (owner/repo as strings? object?), or why the other parameters exist. An agent cannot reliably call this tool 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?

Schema description coverage is 100%, but the schema descriptions are generic templates (e.g., 'HTTPS URL to normalize or cite', 'City name for a public weather hint') that don't align with the tool's stated purpose. The description adds no clarification about which parameters are relevant (e.g., only 'url' matters) or how the 'ref' parameter relates to GitHub parsing. It fails to compensate for the schema's generic nature.

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 clearly states a specific verb ('Parse') and resource ('GitHub URL') and implies extraction of owner/repo, which distinguishes it from siblings like figma-url-shape or jira-key-shape. However, it doesn't mention whether it also validates the URL format, which could be expected given the 'shape' naming convention. Still, 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 guidance on when to use this tool instead of alternatives like normalize-url, web-fetch, or other *-shape tools. It doesn't mention any preconditions (e.g., 'use when you have a GitHub URL'), nor does it exclude other tools. An agent must infer usage 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 must carry the behavioral disclosure burden. It only states the count and title discard behavior, but does not disclose network access, rate limits, or how the numerous parameters are processed. The parameter descriptions in the schema imply they are discarded after checks, but the tool's actual behavior with them remains 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?

The description is extremely concise with two sentences and no fluff, front-loading the purpose. However, it omits usage context, which is a trade-off. For sheer efficiency it earns a 4, but it is under-informative given the tool's 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?

The tool has 9 optional parameters, none required, and no output schema. The description does not explain how the parameters relate to the HN count, what the return value looks like beyond a number, or error conditions. An agent would be unable to correctly invoke this tool without additional information, making it severely incomplete.

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 100%, but the parameter descriptions are generic and unrelated to the tool's purpose (e.g., 'city' for weather, 'ref' for Git). The description does not clarify which parameters affect the HN count or how they are used. An agent cannot determine which parameters to supply, making invocation ambiguous.

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 clearly states the tool counts current Hacker News front-page stories, a specific verb and resource. It is distinct from sibling tools like fetch-status or normalize-url, which are unrelated. The phrase 'Titles discarded' clarifies that only the count is returned, not story titles.

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, nor any conditions or prerequisites. The sibling list includes many other tools, but the description does not mention any exclusions or selection criteria, leaving the agent to infer usage.

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 present, so the description must carry the full burden of behavioral disclosure. It provides zero information about side effects, return format, errors, or how parameters are processed. For a tool with 9 parameters, 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?

The description is a single short sentence, which is concise, but it is under-specified and does not front-load any actionable information. It lacks structure that would help an agent understand what to do with it. The brevity is not an asset when it omits essential context.

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 9 parameters, no output schema, and no annotations, the description is completely inadequate. It does not explain what the tool returns, how to invoke it correctly, or how the parameters interact. This is a severe gap that would leave an agent 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 schema provides descriptions for each parameter, but the tool description adds no meaning beyond that. The parameters (e.g., 'url', 'city', 'host') seem unrelated to IANA timezone names, creating confusion about their purpose. With 100% schema coverage, the baseline is 3, but the description fails to tie the parameters to the tool's stated purpose, so a lower score is warranted.

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 'Common IANA timezone names for clock calls' hints at a purpose but is vague about the actual operation. It does not state whether the tool returns a list, validates a zone, or maps names to something. It is not a tautology but lacks specificity and fails to distinguish it from sibling tools like 'timezone' or 'utc-time'.

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 conditions, prerequisites, or exclusions. The description offers no context to help an agent decide between this and the timezone-related 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?

With no annotations, the description must carry behavioral disclosure. It mentions the output (group counts only) but does not disclose that most parameters are discarded or that the tool performs shape checks rather than a single fetch. This is misleading relative to the schema.

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 concise sentence, but it is under-specified and does not earn its place because it omits the tool's actual multi-purpose behavior. It lacks structure or a clear front-loaded summary of what the tool truly does.

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 nine parameters and no output schema, this description is grossly incomplete. It does not explain the parameters, the actual operation, error behavior, or return format, leaving an agent unable to call it 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 provides 100% coverage for parameter descriptions, so the baseline is 3, but the description adds no parameter semantics and actively contradicts the schema by implying a single-purpose robots.txt fetch. This confuses rather than clarifies how the parameters relate to the tool.

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 ('Fetch a public robots.txt and return group counts only'), but the input schema exposes nine unrelated parameters (ref, city, json, zone, etc.) described as shape checks, which contradicts the stated purpose. It does not distinguish itself from sibling tools like web-fetch or fetch-status.

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 given on when to use this tool versus alternatives. The description provides no context, prerequisites, or exclusions, leaving an agent to guess the intended use case.

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 only states 'Key discarded,' which hints at no side effects but omits whether the tool returns a boolean, performs network calls, or has other behavioral traits. Critical disclosure is missing.

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 (two short sentences), but it sacrifices necessary detail. It is under-specified, omitting how inputs map to the check and what the output is. Being short is not the same as being appropriately concise.

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 9 parameters and no output schema, the description is grossly inadequate. It does not explain the purpose of each parameter, the expected input format for a Jira key, or the return value. An agent cannot reliably invoke 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 coverage is 100%, but the parameter descriptions (e.g., 'Git ref name; discarded after the shape check') are unrelated to Jira keys. The tool description adds nothing to clarify which parameter holds the Jira key, making the schema misleading rather than helpful. Description fails to compensate for the mismatch.

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: 'Check a Jira issue key shape.' It distinguishes from siblings by naming Jira. However, it fails to explain how the 9 varied parameters (ref, url, city, feed, etc.) relate to a Jira key, leaving the operational purpose ambiguous.

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 on when to use this tool versus sibling shape-checkers like domain-shape or github-repo-shape. It implies use for Jira keys but provides no exclusions or alternatives. Context must be inferred, which is insufficient.

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. It discloses that values are discarded, but leaves ambiguity about whether keys are counted recursively, how invalid JSON is handled, and what the output format is. This is minimal behavioral disclosure.

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 very concise (two short sentences) and front-loaded with the action. However, it is arguably too terse, missing important context such as recursion depth or error handling. It is appropriately compact but not sufficiently 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 tool with 9 optional parameters and no output schema, the description is extremely incomplete. It does not clarify key counting semantics (top-level vs nested), expected return type, error conditions, or any behavioral constraints. An agent would have to guess many 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 100%, with each parameter individually described. The description adds no extra parameter meaning, so the baseline of 3 is appropriate.

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 clearly states the action ('Count keys') and the resource ('a JSON object'), and adds a behavioral note that values are discarded. It is distinguishable from siblings like validate-json, though it doesn't name 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?

No guidance is provided about when to use this tool versus alternatives. There is no mention of prerequisites, typical use cases, or exclusions.

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 must carry the full burden of behavioral disclosure. It only states a conversion, offering zero information about side effects, parameter usage, discarding behavior, or return format. The schema does mention 'discarded' for some parameters, but that is outside the description and does not compensate for the lack of 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 phrase, extremely short, but it is under-specified rather than concise. It lacks structure and does not front-load any actionable information. Every useful detail 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?

Given 9 parameters and no output schema, the description is grossly incomplete. An agent cannot infer which parameters are relevant, what inputs to supply, or what the tool returns. The glaring mismatch between the conversion name and the generic parameters compounds the inadequacy.

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 100%, so the baseline is 3. The description adds no meaning beyond the schema; it does not explain how the parameters relate to the conversion. The schema itself provides some semantics (e.g., 'discarded after'), but the description contributes nothing.

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 'Nautical miles to kilometers' states a specific conversion verb and resource, but it is a bare label that fails to connect to the nine generic string parameters (ref, url, city, feed, etc.). The mismatch makes the tool's actual purpose unclear—an agent cannot tell what this tool does with a URL or city name. It is only slightly more than a tautology of the 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 versus any of the 30+ siblings. No conditions, exclusions, or alternative tool names are mentioned. The description leaves the agent to guess its applicability.

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 bears full responsibility. It discloses that query and fragment are dropped, which is useful, but it ignores the nine schema parameters (e.g., city, feed, json) and their behaviors. The schema itself hints at discarding these values, but the description does not explain what the tool actually does with them, leaving significant behavioral ambiguity.

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 conveys the core function and a key behavioral trait (dropping query and fragment). No wasted words; it is efficiently 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?

The tool has 9 optional parameters and no output schema, yet the description only covers URL normalization. It fails to explain the role of the other parameters, the tool's behavior when they are supplied, or any return format beyond the three URL parts. This is incomplete for an agent attempting to call the tool correctly with a non-URL input.

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 100%, so the baseline is 3. The description does not add any parameter-specific meaning beyond the schema's own descriptions. It never mentions how 'url' relates to the other parameters, nor does it clarify that only 'url' is used for the stated output. Thus it provides no added value over the 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 states a specific verb ('Return') and a clear resource ('origin, host, and path for a URL'). It distinguishes from sibling shape-checkers (e.g., browser-url-ok) by implying it returns URL components rather than a boolean. However, it does not acknowledge the schema's other parameters, making the purpose slightly narrower than the tool's apparent scope.

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 given on when to use this tool versus alternatives like browser-url-ok or figma-url-shape. The description only states the function without any context, prerequisites, or exclusions, leaving the agent to infer appropriate usage.

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 carry the behavioral burden. It discloses one behavior: 'No browser is launched.' But it fails to explain what happens with the diverse parameters (e.g., 'discarded after the shape check' for some, 'no disk access' for path). It does not state whether network calls occur, what the return value looks like, or whether side effects exist. The single sentence is far from sufficient.

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 concise (one sentence) and front-loaded with the primary action. However, it is too terse to be useful; it omits essential context about the parameter set and tool behavior. Conciseness without informativeness earns a middle score.

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?

This tool has 9 parameters, no annotations, and no output schema. The description covers only a fraction of the tool's apparent surface area. It does not explain the role of most parameters, the expected inputs, or what 'ok' means as a result. This is severely incomplete for an agent to call it 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 provides descriptions for all parameters (100% coverage), but those descriptions are unrelated to the stated URL-checking purpose (e.g., 'City name for a public weather hint'). The tool description adds no additional meaning to any parameter and does not clarify how the parameters relate to the tool's function. The mismatch between description and schema undermines parameter understanding.

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 action: 'Check whether a URL can be opened.' This is a clear verb and resource. However, the input schema accepts 9 unrelated parameters (city, json, path, zone, query, etc.) that have nothing to do with checking a URL. The description does not reconcile this mismatch, so an agent cannot infer the actual purpose for most parameters. It is not a tautology, but it is incomplete and 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?

No guidance is provided on when to use this tool versus alternatives like 'browser-url-ok', 'fetch-status', or 'normalize-url'. There is no mention of exclusions or conditions. An agent has no basis to decide between this and 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?

With no annotations, the description carries the full burden of disclosing behavior. It notes 'Prompt discarded' but gives no indication of what happens to the nine parameters, whether any validation occurs, or what the output structure is. The schema descriptions hint at checks, but the description itself is silent on these behaviors.

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 sentence, which is efficient, but it is under-specified. It lacks essential information about the template and parameter handling, making it more a placeholder than a useful definition. Under-specification is not 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 tool with nine parameters, no output schema, and no annotations, the description is extremely incomplete. It does not explain what the template looks like, why the parameters exist, what the tool actually does with them, or what the return value contains. An agent cannot call this tool correctly based on this description 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 schema provides 100% coverage with detailed descriptions for each parameter, so the baseline is 3. The tool description adds no meaning beyond the schema and does not explain why a thinking template tool accepts parameters like city, URL, or zone, so it fails to compensate for the semantic disconnect.

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 it returns a three-step thinking template, which is a specific verb and resource, but the template's content and purpose are vague. It does not differentiate this tool from the many siblings, several of which also return structured output, so an agent cannot tell what makes this tool unique.

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 offers no guidance on when to use this tool versus its 27 siblings. It mentions 'Prompt discarded' but does not explain any conditions or alternative tools, leaving the agent to guess based on 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'current time' which implies a read, but it does not disclose any side effects, authentication requirements, rate limits, or output format. The presence of nine parameters with 'discarded' notes in the schema is not reflected in the description, so behavioral context is minimal.

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, concise sentence with no filler. It is front-loaded with the core purpose, which is efficient. However, its brevity borders on under-specification, though it is appropriately sized for the minimal stated purpose.

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 nine parameters, none required, and no output schema. The description does not explain how to invoke it (which parameter to use) or what the response looks like. It also does not address why unrelated parameters exist in the schema, leaving significant gaps for an agent trying to use it 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 100%, but the tool description adds no meaning beyond what the schema already states. Moreover, the schema includes many unrelated parameters (ref, url, city, etc.) with descriptions like 'discarded', and the description does not clarify that only the 'zone' parameter is relevant for this tool. This ambiguity hinders correct parameter selection.

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 'Current time in a named IANA timezone.' clearly states the action (providing current time) and the resource (a named IANA timezone). It implicitly distinguishes from sibling tools like utc-time (likely gives UTC) and iana-zones (likely lists zones), though it does not explicitly name 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 such as utc-time or iana-zones. There is no mention of context, prerequisites, or exclusion conditions, leaving the agent to infer usage.

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 must fully disclose behavior. The only behavioral note is 'The body is discarded,' which is a minimal safety disclosure. It does not state whether the tool returns a boolean, throws an error, or what happens on invalid input. There is no mention of side effects, rate limits, or output format, leaving the agent to guess at the tool's behavior.

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 concise—only two short sentences. While it avoids verbosity, it is too under-specified to be genuinely helpful. It does not front-load any critical information beyond the basic purpose, and the 'body is discarded' note is the only additional context. The brevity borders on under-specification rather than effective 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 tool with nine optional parameters and no output schema or annotations, this description is woefully incomplete. It does not explain what 'body' means, how the parameters interact, what the return value is, or how errors are signaled. An agent has no way to know whether this tool is appropriate for a given task or how to interpret its result. The description fails to provide the essential context needed for correct usage.

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 100%, so every parameter is documented with its own description. The tool description adds no additional meaning beyond what the schema already provides; it merely restates that the body is discarded, which is also noted in the 'json' parameter description. The description does not explain how the other eight parameters relate to the main JSON validation action, but the schema already covers each parameter individually, so a baseline score of 3 is appropriate.

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 and resource: 'Check whether a body is valid JSON.' It is specific to JSON validation and distinguishable from sibling tools like 'domain-shape' or 'wiki-title-ok'. However, the term 'body' is ambiguous—it could refer to the 'json' parameter or an HTTP request body—and the description does not clarify which parameter it refers to, nor does it acknowledge the presence of nine other unrelated parameters.

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 any alternative. It does not mention any conditions, prerequisites, or exclusions. An agent has no information about when JSON validation is appropriate or how it differs from similar shape-checking siblings like 'domain-shape' or 'file-path-ok'.

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. It only mentions weather and does not disclose that the tool also processes URLs, JSON, paths, queries, etc., as shown in the schema. This is misleading—an agent seeing the schema would be confused about the tool's actual behavior, since the description contradicts the apparent multi-purpose nature. The schema descriptions say parameters are 'discarded' or 'checked', implying a more complex tool, but the description fails to convey that.

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 sentence, efficient and front-loaded with the main purpose. However, it is too brief given the tool's complexity, omitting crucial information about the other parameters and behaviors. It earns a 4 for brevity but not for completeness.

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?

This tool has 9 parameters, no output schema, and no annotations. The description only covers the city/weather use case, leaving the other eight parameter types unexplained. An agent cannot infer how to use the tool for URL, JSON, timezone, or other inputs. The description is severely inadequate for the tool's actual scope.

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 100%, so all parameters have descriptions in the schema. The tool description adds no parameter-specific meaning beyond what the schema already provides. Baseline 3 applies because the schema does the heavy lifting.

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 purpose for the weather use case ('Current temperature for a city via Open-Meteo'), with a specific verb and resource. However, it does not mention the other capabilities implied by the input schema (URL normalization, JSON validation, timezone, etc.), so an agent cannot tell that this tool serves multiple functions. It partially distinguishes from siblings but is incomplete.

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 given on when to use this tool versus alternatives like 'geo-hint' or 'web-fetch'. The description does not mention any exclusions, prerequisites, or context for choosing this tool. An agent must rely on the schema and sibling names, which is insufficient.

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. It discloses that the body is discarded, which is useful, but it does not mention other behaviors such as redirect handling, timeouts, authentication, or how the many other parameters are processed. The schema suggests these parameters are used for various checks but are discarded, yet the description offers no explanation of this multi-purpose behavior.

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 brief and front-loaded with the primary function, avoiding waste. However, it is under-specified given the tool's complexity, so it earns a 4 rather than a 5 for being concise but not comprehensive.

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 9 optional parameters, no output schema, and no annotations. The description covers only the URL-status/content-type behavior, leaving the purpose of the other eight parameters completely unexplained. An agent would not know why ref, city, or json parameters are accepted or how they influence the call. This is a significant gap for a tool with such a wide parameter surface.

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 100%, so the baseline is 3. The description itself adds no parameter-specific information; it only mentions URL implicitly. The schema's own descriptions are present but cryptic (e.g., 'discarded after the shape check'), and the tool description does not clarify how these parameters relate to the stated purpose.

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: it retrieves HTTP status and content type for a public URL, and explicitly notes the body is discarded. This clearly differentiates it from tools like fetch-status that may return full bodies, but it fails to mention the other eight schema parameters (ref, city, feed, etc.), leaving the tool's full scope ambiguous.

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 siblings like fetch-status, normalize-url, or browser-url-ok. The description gives a general capability but does not state exclusions, alternatives, or specific scenarios where this tool is preferred.

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. The only behavioral note ('Title discarded after the call') is contradicted by the schema's own disposal semantics ('discarded after the shape check', 'no disk access', 'discarded after the length check'), which describe a generic input validator rather than a Wikipedia title check. The behavior described does not match the 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 short (two clauses), which is structurally concise, but the brevity serves misleading content. Conciseness only earns credit when the content is accurate; here it packages a false purpose into a compact statement.

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 tool with no output schema and no annotations, the description should at least clarify the tool's purpose and which inputs it expects. Instead it describes a completely different function. Nothing an agent needs to call this tool correctly is present; the description is not just incomplete but actively wrong.

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?

Although schema coverage is 100%, the description's stated purpose maps to zero of the 9 parameters. There is no 'title' parameter, so an agent cannot determine which field holds the Wikipedia title the description asks it to check. The description adds no clarifying meaning to any parameter and in fact conflicts with all of 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 states a specific verb+resource ('Check whether a Wikipedia title exists'), but it is misleading: none of the 9 schema parameters (ref, url, city, feed, host, json, path, zone, query) represents a Wikipedia title. An agent following this description would look for a title parameter that does not exist, so the stated purpose is disconnected from the tool's actual input surface.

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 reference to any of the 28 sibling tools. Worse, the implied usage (Wikipedia title lookup) contradicts the actual parameters (URL, ref, JSON, timezone, etc.), which resemble the shape-checking siblings like file-path-ok and validate-json. The description would actively misroute an agent to the wrong inputs.

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