16 hex chars

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 page content is not stored, which is useful behavioral context, and implies the tool performs an HTTP fetch to determine status. However, it does not mention rate limits, caching, whether the URL is fetched or merely parsed, or what happens on redirects or failures.

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. It is appropriately concise, though it sacrifices contextual completeness for 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?

The tool has 4 parameters, 0 required, no annotations, and no output schema, yet the description only mentions the URL's host/scheme/status. It does not clarify what 'host', 'json', and 'zone' parameters do at the tool level, what the return format is, or how the tool handles omissions. This is inadequate for an agent to confidently invoke 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 100%, so the baseline is 3. The description adds the high-level purpose but does not explain how the four unrelated parameters (url, host, json, zone) relate to each other or when each should be provided. Since all parameters are optional and the schema descriptions are terse, some cross-parameter guidance would have elevated this score.

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 resource ('host, scheme, and HTTP status for a URL'), which clearly indicates what the tool does. It does not, however, differentiate it from sibling tools like normalize-url or validate-time, so it lacks sibling distinction.

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 such as normalize-url, validate-json, or validate-time. The negative constraint 'Page content is not stored' weakly implies a privacy-safe choice, but there is no explicit when-to-use or when-not-to-use guidance.

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 does add one concrete behavioral trait: 'No identifiers are retained,' which signals a privacy/stateless property. However, it does not disclose whether the operation is read-only, whether any data is transmitted, or what side effects exist, so the disclosure is only partial.

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 short, front-loaded, and contains no filler. Each sentence has a purpose: one states an intent, the other states a privacy guarantee. It loses a point because the main intent sentence is vague and does not carry enough meaning to stand alone.

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 four optional parameters, no output schema, and a large sibling set, this description is not complete enough for correct tool selection or invocation. It never explains what classification output the agent should expect, how the parameters affect the call, or when this tool is relevant. The privacy note is the only context beyond 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?

Schema description coverage is 100%: url, host, json, and zone each have their own schema-level descriptions. The tool description adds no parameter-level meaning and does not explain how these parameters relate to the classification result, 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 says 'Show how this request is classified' but never defines what classification means, what resource is being acted on, or what the result looks like. It is distinguishable from sibling tools like validate-json or normalize-url only by the tool name, not by the description. This is vague rather than tautological, so it earns a 2.

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 tool versus any of its siblings. It does not state prerequisites, exclusions, or alternative tools. An agent has no basis for choosing compatibility over validate-json, citation, domain-shape, or normalize-url.

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 discloses only the absence of WHOIS/ownership data, while the schema implies other behaviors (e.g., JSON validation with results 'discarded after the check', URL normalization/citation) that the description completely omits, leaving an incoherent behavioral picture.

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 with the main verb front-loaded, so it is technically concise. However, the brevity sacrifices essential scope information, and the one sentence does not earn its place because it misaligns with the actual parameter set.

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 4-parameter tool with no output schema and no annotations, this description is severely incomplete. It does not state what the tool returns (labels array? delimiter behavior?), how each parameter is used, or why unrelated parameters like 'json' and 'zone' exist in a hostname-splitting tool.

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-level meaning and does not explain how 'url', 'host', 'json', or 'zone' relate to splitting a hostname into labels, but the schema already documents each parameter individually.

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 ('Split a hostname into labels'), but this conflicts with the input schema, whose parameters cover URL normalization, JSON validation, and timezone names. The scope is therefore unclear and potentially misleading; the 'without WHOIS or ownership data' caveat does not reconcile the mismatch.

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. The only hint is the exclusion 'without WHOIS or ownership data,' which tells an agent what the tool does not do, but never when to select it or what its relationship to sibling tools is.

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 discloses no behavior: no side effects, no return format, no error cases, no interpretation of the '16 hex chars' result. The description is essentially content-free.

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, but this is under-specification rather than concise, efficient writing. It lacks any structure or front-loading of useful information; a single vague phrase is not adequate as a tool description.

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 4 optional parameters, no output schema, no annotations, and an unclear operation, the description is wholly insufficient. An agent cannot determine what inputs to provide, what the tool returns, or why it exists among the listed 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?

Schema description coverage is 100%, so the baseline is 3. The description adds no meaning beyond the schema and does not clarify how url, host, json, or zone relate to a 16-character hex string, but the schema itself documents each 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 '16 hex chars' is a noun phrase that merely restates the tool's name without any verb or resource. It doesn't say whether the tool generates, validates, or extracts a 16-character hex string, nor how the four schema parameters relate to 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?

There is no guidance on when to use this tool or when to prefer one of the siblings. Given related tools like normalize-url, validate-json, and timezone, the description gives an agent no basis for choosing hex-16.

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, and it provides none. It does not mention side effects, validation behavior, data handling, or anything about what actually happens when the tool is invoked.

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 and front-loaded, but it is under-specified rather than appropriately concise. The single phrase does not earn its place because it fails to explain the tool's function.

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 four heterogeneous parameters and no output schema or annotations, this description is severely incomplete. It does not explain how url, host, json, and zone relate to the stated purpose, leaving an agent unable 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 input schema has 100% description coverage, so parameters are already well documented. The tool description adds no additional meaning, keeping this at the baseline.

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 noun phrase, not a statement of action. It mostly restates the tool name ('IANA timezone names') and gives no verb or resource operation, and it does not align with the schema, which also accepts URL, host, and JSON 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 alternatives. The phrase 'for clock calls' hints at a context but does not explain how to decide between this tool and the sibling 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?

With no annotations, the description carries the full burden. It does disclose the central behavior: it fetches an external resource and returns only aggregated counts rather than the raw file. However, it omits key edge behaviors such as 404/missing robots.txt handling, redirects, timeouts, rate limits, or the meaning of a 'group count'.

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 tightly written sentence that front-loads the action and the outcome with zero filler. It loses a point because it is terse to the point of omitting the definition of 'group counts' and any parameter mapping, which matters given the mismatched schema.

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 four optional parameters that are only loosely related to the tool's purpose, the 10-word description leaves too much unsaid. An agent lacks the information to choose a parameter confidently, interpret the returned counts, or anticipate failure behavior for a network fetch.

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%, which normally warrants a baseline of 3, but the schema descriptions are clearly mismatched with the tool's purpose: 'url' mentions normalizing or citing, 'json' is to validate and discard, and 'zone' is a timezone name—none relate to robots.txt. The description does not tell the agent which of the four optional parameters to populate, so an agent cannot determine whether to pass url, host, both, or why json/zone exist at all.

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 uses a specific action ('Fetch'), a clear resource ('a public robots.txt'), and a distinct result ('return group counts only'). The 'only' qualifier helps differentiate it from a sibling that might return the full robots.txt, though 'group counts' is not defined.

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 alternatives, no exclusions, and no conditions. The word 'public' implies a constraint, but the description never states when to prefer a sibling or what inputs are required to trigger the fetch.

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 one useful behavioral trait: 'Query and fragment are dropped.' With no annotations, the description carries the full burden, but it does not clarify behavior for the other parameters, error handling, or output format, leaving gaps.

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 and front-loaded: it states the main behavior in the first sentence and the key transformation in the second. No filler words, though it is too narrow for the full parameter set.

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 four parameters and no output schema, so the description needs to explain what the tool returns and how all inputs contribute. It only covers `url`, leaving `host`, `json`, and `zone` unexplained, and fails to specify the return format beyond listing fields.

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%, giving a baseline of 3, but the tool description only adds semantics for the `url` parameter (dropping query/fragment). It fails to explain how `host`, `json`, and `zone` relate to the tool's stated purpose, so the description actually introduces confusion rather than compensating for schema gaps.

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 resource ('origin, host, and path for a URL'), making the core purpose clear. However, the schema includes unrelated parameters (`json`, `zone`) that the description does not acknowledge, which muddies the overall 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 explicit when-to-use or when-not-to-use guidance is provided, and no alternatives are mentioned. The description implies it is for URL component extraction, but the presence of `json` and `zone` parameters without explanation leaves usage context ambiguous.

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. A one-line 'Short catalog' reveals nothing about side effects, return values, error handling, or execution behavior. The only behavioral hint ('discarded after the check') lives in the schema for the json parameter, not in 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 text is short and void of fluff, but it is under-specification rather than conciseness. A single fragmentary sentence 'Short catalog of common HTTP status codes' provides almost no operational content for a tool with four heterogeneous 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 four optional parameters, no output schema, no annotations, and a clear sibling set, the description is drastically insufficient. It does not state what the tool returns, how parameters map to behavior, whether parameters are alternative modes or combinable inputs, or when the tool is applicable.

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. Each parameter has a reasonable standalone description (e.g., 'JSON text to validate; discarded after the check'). However, the description adds zero connection between these parameters and the tool's stated purpose of an HTTP status code catalog — the semantic glue is 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 identifies the resource (HTTP status codes) but lacks any verb indicating the action — does the tool list codes, look them up, or generate them? It also does not differentiate itself from siblings like citation, validate-json, or timezone, whose parameter names (url, host, json, zone) seem to be borrowed from them, making the actual purpose confusing.

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 mentions no parameters, no context, and no conditions, leaving an agent unable to decide between status-catalog and its siblings. Zero guidance.

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, yet it only states the output. It does not mention error handling for invalid zones, whether the tool is read-only, or why the schema includes url, host, and json parameters that appear unrelated to timezone lookup.

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 well-formed sentence that is front-loaded with the core purpose. There is no filler or redundant restating of 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?

Despite being a simple tool, the schema introduces four parameters with no indication of which are needed or why the three URL/JSON-related parameters exist. The description also omits output format, error behavior, and whether the zone parameter is required, leaving an agent without enough context to call the 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 100%, so the baseline is 3. The schema documents each parameter individually, but the description adds no clarification about which parameter is actually relevant or why url, host, and json appear on a timezone tool. The zone parameter aligns with the description, but the mismatch among the other parameters is confusing.

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 identifies the action (retrieve current time) and the resource (IANA timezone). It also easily distinguishes this tool from the URL/JSON-focused siblings like normalize-url and validate-json.

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 tool versus alternatives, no mention of required parameters, and no exclusions. The description simply states what the tool returns, leaving the agent to infer usage context from the tool name and schema.

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, but it only states the result without saying what format the timestamp uses or whether the input parameters are ignored. The unrelated schema properties (url, host, json, zone) create additional ambiguity that the description does not resolve.

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 and front-loaded, but it is more under-specified than genuinely minimal. It omits an action verb and fails to address the confusing input schema, so the brevity comes at the cost of 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?

Given the mismatched 4-parameter schema and absence of annotations or an output schema, the description is not sufficient for reliable invocation. An agent cannot determine expected output format, whether parameters are ignored, or why the schema contains unrelated fields.

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 description coverage is 100%, the parameters are semantically disconnected from the tool's stated purpose: none of url, host, json, or zone is obviously relevant to obtaining a UTC timestamp. The description adds no clarification about which parameters, if any, should be supplied, so the agent cannot confidently choose or combine 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 'Current UTC timestamp' clearly communicates that the tool returns the current UTC time, and the name reinforces this. However, it lacks an explicit verb like 'returns' or 'gets', and it does not differentiate itself from the sibling timezone or iana-zones tools.

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 such as timezone or iana-zones. The description also gives no hint that the input schema parameters are optional or how they relate to the operation, leaving invocation decisions entirely to inference.

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 burden of behavioral disclosure. It adds one useful behavioral fact—'The body is discarded'—which clarifies that the tool has no persistent side effect. However, it does not describe what the tool returns (e.g., true/false, validation report) or clarify that only the 'json' parameter is relevant while 'url', 'host', and 'zone' are likely ignored.

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 short sentences, front-loaded with the core purpose and no filler. Every word earns its place, and the discard note is an efficient addition.

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 no output schema and no annotations, this description is incomplete. It fails to specify that three of the four schema parameters ('url', 'host', 'zone') appear irrelevant to the JSON-validation task, and it does not state the return format. An agent would need to guess what a successful or failed validation 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 100%, so the schema already documents all four parameters. The description adds no further meaning about how the parameters relate to the validation operation, leaving the agent to infer that only 'json' matters. Baseline 3 is appropriate since the schema does most of the work.

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 uses a specific verb and resource: 'Check whether a body is valid JSON.' The purpose is immediately clear and the tool name matches. It does not explicitly differentiate from siblings, but the operation is distinct enough that an agent can infer what it 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?

There is no guidance on when to use this tool versus alternatives, no mention of preconditions, and no exclusion criteria. The description simply states what it does, not in what context an agent should choose it over sibling tools like normalize-url or cite.

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