GitHub Repo Shape

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

The description mentions that task text is discarded and that it returns connection methods, but it does not disclose whether the tool makes external calls, incurs costs, or has side effects. With no annotations, the description carries the full burden of transparency and does not satisfy it.

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 brief and contains no filler or redundant content. However, the brevity may contribute to the lack of clarity and 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?

With nine optional parameters, no output schema, and no annotations, the description is far too incomplete. It does not explain what 'connection methods' means, what kind of result to expect, or how to provide a meaningful task 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?

All nine parameters have descriptions, but those descriptions are cryptic and unrelated to the tool's stated purpose, e.g. 'ref' is a Git ref name discarded after a shape check, and 'query' is search text discarded after a length check. They do not explain how the parameters should be used to find a tool gateway.

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 finds a public pay-per-call tool gateway for tasks like weather, search, scrape, or voice, and returns connection methods. However, it does not specify exactly what kind of gateway or how the tool's parameters correspond to those tasks.

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 usage guidelines are provided. There is no indication of when to use this tool versus the many sibling tools such as weather-hint, normalize-url, or validate-json, nor any scenarios 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?

The description discloses one behavioral aspect: no browser is launched. This is useful for understanding side effects but omits other potential behaviors like network requests, timeout handling, or criteria for 'can be opened'. Given the absence of annotations, more transparency would be beneficial.

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, consisting of two short sentences. It avoids unnecessary wording and gets to the point quickly. No redundancy or filler content.

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 description covers the basic function but lacks critical context. It does not specify what 'can be opened' means (e.g., HTTP status, connectivity), what the output format is (no output schema), or how the numerous parameters affect the check. For a simple tool, it may be minimally adequate, but given the parameter confusion, more explanation is needed.

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?

While the schema descriptions cover 100% of parameters (each has a short description), many parameters (ref, city, feed, json, path, zone, query) seem unrelated to the tool's stated purpose of checking URL accessibility. The descriptions are generic and do not explain how these parameters relate to the URL check, causing confusion. The tool's focus is unclear from the parameter set.

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's action ('Check whether a URL can be opened') and resource (URL). However, it does not distinguish this tool from sibling tools like 'playwright-url-ok' or 'fetch-status', which likely serve similar purposes. The added note 'No browser is launched' hints at a lightweight nature but does not explicitly differentiate.

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 a single usage hint ('No browser is launched'), implying a non-interactive check. However, it lacks explicit guidance on when to prefer this tool over alternatives, such as 'fetch-status' or 'web-fetch'. No conditions or example scenarios are given.

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

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

No annotations are provided, and the description only says 'Expression discarded.' This does not disclose side effects, persistence, read-only behavior, error conditions, or what happens with the provided parameters. The statement is meaningless because no expression parameter exists.

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

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

The description is extremely short and thus technically concise, but it omits critical information and includes a nonsensical phrase. Being brief is not helpful when the content is misleading and fails to address the actual 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 9 parameters, no output schema, no annotations, and a description that contradicts the parameter names and descriptions, the tool is completely underspecified. An agent cannot correctly infer how to invoke this tool or interpret its 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?

Although every parameter has a schema description, those descriptions are irrelevant to the stated arithmetic purpose (e.g., 'Git ref name; discarded after the shape check'). The description does not explain how any of these 9 parameters relate to evaluating an arithmetic expression, so the parameter semantics are completely disconnected from the tool's 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 claims the tool evaluates 'a+b style arithmetic', but no arithmetic expression parameter exists in the schema. The actual parameters are unrelated string fields like ref, url, city, and query, making the tool's true purpose unclear and potentially misleading.

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

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

There is no guidance on when to use this tool versus any of the many sibling tools. The description does not explain selection criteria, scenarios, or alternatives, leaving the agent with no basis for choosing calc-eval.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add a useful privacy guarantee ('Page content is not stored'), but it omits other relevant traits such as whether a network request is made, error behavior, or rate-limit implications.

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 with no filler. The purpose is front-loaded, and the second sentence adds a meaningful behavioral caveat rather than repeating the 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?

Despite having 9 parameters and no output schema or annotations, the description is extremely brief. It does not explain the role of the other parameters, error cases, return format details, or how this tool relates to its siblings. The schema covers parameter meanings, but the overall context is incomplete for such a multi-purpose-looking 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 adds no parameter-level meaning beyond the schema; it only highlights that the tool works 'for a URL', which the schema already conveys for the url 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 clearly identifies the verb ('Return'), the resource ('a URL'), and the outputs ('host, scheme, and HTTP status'). It is specific enough to understand the core function, though it does not explicitly differentiate itself from siblings like normalize-url, fetch-status, or web-fetch.

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 its many siblings. The description does not state which conditions favor citation over fetch-status, normalize-url, or web-fetch, leaving the agent to infer the appropriate 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?

With no annotations, this description carries the full burden of disclosing behavior. It does add 'No identifiers are retained,' which is a useful privacy statement, but it doesn't say whether the tool is stateless, whether it makes external calls, whether it has any side effects, or what the actual return value looks like. This is incomplete for an unannotated 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 only two sentences with no filler. It front-loads the main statement ('Show how this request is classified') and then adds a privacy note. The brevity itself is a strength, though the wording could be much clearer.

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 having all parameters documented in the schema, the tool's overarching purpose is ambiguous and there is no output schema. The tool has 9 optional inputs and no required ones, but the description does not explain what classes/outputs the user can expect. The agent cannot confidently call this common tool to get a usable answer.

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%, and the input schema provides both a description and discard/security note for each of the nine parameters (e.g., 'no disk access', 'discarded after shape check'). The tool description itself adds no parameter-level meaning, but the schema already covers that. Thus, 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 states only 'Show how this request is classified.' This is a vague statement: it doesn't specify what classification means, what is being classified, or why a user would call this tool. It does not effectively distinguish 'compatibility' from the many sibling tools (browser-url-ok, validate-json, etc.) because it gives no clue as to what set of labels or categories are involved.

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 about when to use this tool versus the 25 siblings. There are no conditions, no if/when rules, no mention of an alternative tool. The description is just a one-line instruction without any decision framework.

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 the network method (HEAD), the scope (public URL), and that only status is returned. However, it does not mention redirect handling, timeout behavior, error cases, or output format, leaving some 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?

The description is a single concise sentence with no redundancy. It is short and direct, though it sacrifices explanatory detail.

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

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

There is no output schema, no mention of return status codes, and no explanation of how the many unrelated parameters are used. Given the large optional parameter set, the description is severely incomplete for an agent to use the tool reliably.

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 includes nine optional parameters, but their descriptions are largely inconsistent with the stated purpose. Descriptions like 'discarded after the shape check', 'to normalize or cite', and 'no disk access' are unrelated to checking URL status, and even the url parameter description mentions 'normalize or cite' rather than HEAD.

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?

Description clearly states the tool performs a HEAD request on a public URL and returns only the status code. This distinguishes it from content-fetching or validation siblings, though the name suggests a broader fetch operation.

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

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

No explicit guidance is given about when to use this tool versus alternatives like browser-url-ok, web-fetch, or status-catalog. The description implies a lightweight status check, but does not state 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?

The description states that the path is discarded, which is a behavioral detail, but it does not mention side effects, permissions, errors, return behavior, or any safety-relevant traits. With no annotations present, the description carries the burden and provides very little transparency.

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 has no filler, which is good, but it is under-specified and the second sentence ('Path discarded.') is cryptic. It lacks a clear structure connecting the action to the parameters or expected behavior.

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 description does not explain what 'shape' means, what output is produced, how the path is discarded, or which of the nine optional parameters should be used. Given the complex and inconsistent schema, the description is far from complete enough for an agent to use 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?

Although the schema has 100% description coverage, many parameter descriptions are unrelated to the stated purpose (e.g., city, feed, json, query) and appear copied from other tools. The tool description does not clarify which parameters are relevant or how they map to parsing a Figma URL, so the parameter semantics are misleading rather than helpful.

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

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

The description names a specific action ('Parse') and resource ('Figma file URL'), giving a basic sense of purpose. However, 'Path discarded' is ambiguous and the tool name suggests validation/shape-checking rather than parsing, so the intended behavior is not fully clear.

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 about when to use this tool instead of any sibling tool. There is no mention of prerequisites, context, or alternative tools, so an agent has no basis for selecting or invoking it appropriately.

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 is the only source of behavioral disclosure. It does state 'No disk access', which is a useful constraint, but it omits what happens with each parameter, whether multiple parameters can be supplied, or what the response looks like. This is a significant gap for a tool with such a broad 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, which is structurally clean and front-loaded with the core idea. However, it is so sparse that it under-specifies the tool's capabilities, especially given the nine parameters. Conciseness is not an asset when it sacrifices necessary 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?

The tool has nine optional parameters, no output schema, and no annotations. The description addresses only 'path' and doesn't explain the role of the other eight parameters, nor any expected return values or error conditions. This is completely inadequate for an agent to invoke the tool correctly in any non-trivial scenario.

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 descriptions are generic and unhelpful (e.g., 'discarded after the length check'). The tool description fails to explain how these parameters relate to the stated purpose of checking paths, leaving the agent confused about why fields like 'city' or 'feed' exist. The description adds no meaningful value beyond 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 'Check whether a path looks safe' which identifies a verb and resource, but it is vague about what 'safe' means and fails to differentiate from siblings like domain-shape or browser-url-ok. More critically, the schema lists nine unrelated parameters (city, feed, json, etc.), yet the description only mentions paths, making the actual scope 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?

The description gives no guidance on when to use this tool versus alternatives. It only mentions 'No disk access' as a constraint but doesn't state when to prefer this over sibling tools or what conditions disqualify it. Agents would have to infer usage from the terse text, 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?

There are no annotations, so the description must carry transparency. It discloses the external Open-Meteo dependency but does not mention side effects, read-only behavior, or data handling; the schema's 'discarded' notes are not in the tool 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 short sentence with no filler; the core purpose is front-loaded and the Open-Meteo dependency is included.

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 description is too sparse for the actual input schema: nine optional parameters, no output schema, and no annotations. It does not explain which parameter is the place, how to interpret the output, or how to handle the unrelated parameters.

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

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

With 100% schema coverage, the baseline is 3, but the description adds no mapping between 'place' and any parameter, and the city parameter description ('public weather hint; discarded') conflicts with the geocoding purpose, leaving the relevant input 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 returns latitude/longitude for a place via Open-Meteo, which distinguishes it from siblings like weather-hint. It lacks an explicit verb and doesn't identify the input parameter, but the core function is understandable.

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 about when to choose this tool over alternatives; it doesn't mention weather-hint or any other sibling, nor does it state the intended use case beyond the short description.

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 disclosing side effects; it only says 'Count' and 'Titles discarded,' but does not state whether the tool is read-only, whether it makes a network request, or what the output format is.

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 the phrase 'Titles discarded' is cryptic and adds ambiguity without contributing useful 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 no output schema and 9 optional parameters, the description is incomplete: it does not explain what the tool returns, how the parameters affect the count, or whether they are ignored entirely.

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 all 9 parameters have schema descriptions, many are clearly unrelated to counting HN stories (e.g., 'Git ref name', 'IANA timezone name', 'Search text'), and the tool description does not clarify which parameters are actually meaningful or ignored.

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

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

The description names a specific action ('Count') and resource ('current Hacker News front-page stories'), making the tool's purpose immediately clear and distinguishing it 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 about when to choose this tool over alternatives; it does not mention relationship to web-fetch, normalize-url, or other siblings, nor any conditions under which it should or should not be used.

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 disclose behavior, but it does not. There is no mention of read-only access, side effects, return values, or how inputs are handled. The description is entirely absent on the tool's runtime 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 one-sentence description is efficient and front-loaded with the core noun phrase, but it is under-specification, not careful conciseness. A tool with nine parameters and no annotations needs more than a fragment, even if the fragment is sparing.

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 nine parameters, no output schema, and no annotations, a single sentence naming the resource is utterly incomplete. An agent cannot determine which parameters to pass, what to expect as a return value, or how to handle errors, leaving the tool effectively unusable.

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%, setting a baseline of 3. The description adds no value in explaining how the nine parameters relate to the tool's purpose—for example, it does not highlight that 'zone' is the key parameter or clarify the role of 'url', 'city', or 'path' in a timezone-name tool. Still, 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 identifies the resource (common IANA timezone names) and a context (clock calls), but it uses a noun phrase rather than a verb, so it is ambiguous whether the tool returns a list, validates a zone, or does something else. It distinguishes from sibling 'timezone' only by hinting at a catalog, but does not state an explicit action.

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 phrase 'for clock calls' gives a general use context, but there is no guidance on when to choose this tool over alternatives like 'timezone' or 'utc-time', and no mention of exclusions or conditions. An agent cannot infer the right selection criteria.

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, but it only says it fetches and returns group counts. It doesn't mention network access, error handling (e.g., missing robots.txt, invalid URL), any rate limits, or that other parameters are ignored. The schema descriptions hint at discarding values, but the tool description itself offers no behavioral context beyond the return type.

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, tightly worded sentence with no filler. It is front-loaded with the action and resource, and the phrase 'group counts only' immediately sets expectations. Every word contributes meaning, making it highly concise and well-structured.

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

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

Despite the schema covering all parameters, the description is incomplete for a tool with 9 optional parameters and no output schema. It fails to identify which parameter is the core input (url) or to explain why other parameters exist (e.g., they are used for shape checks but discarded). There's no mention of error behavior or the format of the returned group counts, leaving the agent with insufficient guidance for correct invocation.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-specific meaning; it doesn't clarify which parameter is the primary target (likely 'url') or that all others are ignored. Since the schema already documents each parameter, the description adds no extra value, keeping it at 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 states a specific action (Fetch), a specific resource (public robots.txt), and the exact return (group counts only). This clearly distinguishes it from generic fetch tools like web-fetch or fetch-status, and the 'public' qualifier clarifies scope. It is not a tautology and names the output precisely.

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. It doesn't mention that it's only for robots.txt, nor does it exclude cases like private robots or non-robots content. There is no reference to sibling tools like web-fetch or fetch-status, leaving the agent to infer the appropriate 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?

Only states 'Key discarded' implying no persistence, but no other behavior, side effects, or permissions are mentioned.

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

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

The description is short but lacks essential structure; it fails to specify the input mechanism, making brevity counterproductive.

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?

Missing critical context about which parameter to use for the Jira key check; the tool cannot be used correctly with the given 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?

All 9 parameters are described as 'discarded' or irrelevant, yet none is identified as the Jira key to check, leaving parameter semantics completely unclear.

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 'Check a Jira issue key shape' but does not clarify which parameter holds the Jira key, making the 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 is provided about when to use this tool versus alternatives like domain-shape or github-repo-shape, nor any context for appropriate input.

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 phrase 'Body discarded' hints that the response body is not retained, but it does not disclose whether the tool has side effects, permissions requirements, or rate limits. With no annotations provided, the description carries the full burden but only partially covers behavioural transparency.

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 concise and front-loaded with the core action. However, it is too sparse to convey necessary context, sacrificing completeness for brevity. It is not overly verbose, but the information density is low.

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 nine optional parameters and no output schema, the description is severely incomplete. It does not explain the return format, how to interpret the HTTP status, or how the disparate parameters interact. An agent would be unable to use this tool effectively based solely on the provided 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 description does not explain any of the nine input parameters. While the schema provides short descriptions for each (e.g., 'City name for a public weather hint'), the tool description itself is silent on how parameters like 'city', 'zone', 'json', or 'query' relate to checking HTTP status for library docs. This leaves parameter semantics entirely 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 states a verb ('HTTP status') and a resource ('public library docs URL'), giving a basic sense of purpose. However, it is vague about what constitutes a 'public library docs URL' and does not explain how the other input parameters fit into this purpose, so clarity is moderate.

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 sibling tools like fetch-status or web-fetch. It does not mention any conditions, alternatives, or exclusions, leaving the agent without direction on tool 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?

The phrase 'Values discarded' gives some behavioral hint, but the description does not explain the return format, error handling for invalid JSON, or whether inputs are consumed. With no annotations available, this is insufficient.

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, but it is too sparse to be useful. It omits the critical mapping between the tool's purpose and the provided 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?

The tool lacks an output schema and the description does not state what is returned, how the JSON object should be supplied, or what errors can occur. The presence of 9 optional unrelated parameters compounds the incompleteness.

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 describes each parameter, those descriptions are unrelated to counting keys in a JSON object. The 'json' parameter is described as validation/discard, not key counting, and the other parameters appear to be copied from unrelated tools.

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 the action ('Count keys in a JSON object') but does not identify which input parameter contains the JSON object. The 9 unrelated string parameters make the intended 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 is given about when to use this tool versus sibling tools such as validate-json, search-query-len, or other checking tools. There is no indication of appropriate or inappropriate use cases.

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 that query and fragment are dropped, which is useful behavioral information. With no annotations, it omits error handling, invalid-URL behavior, and whether any network access occurs.

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. The core behavior is front-loaded and easy to parse.

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, the description lacks essential context. It does not define the result format, parameter roles, or usage preconditions, leaving an agent to guess.

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

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

The tool description addresses only the URL concept, while the schema lists nine parameters and most seem unrelated (e.g., city, feed, zone, ref). The description does not clarify which parameters are actually used or how they 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 clearly states it returns origin, host, and path for a URL and explicitly mentions dropping query and fragment. It is specific enough to distinguish from most siblings, though it does not explicitly contrast with other URL-related 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 given on when to use this tool versus URL-related siblings like browser-url-ok or fetch-status. The description only explains the transformation, not the intended use case 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 bears full responsibility for disclosing behavior. It fails to mention that the tool likely performs a network request, what 'can be opened' means in practice, timeouts, or side effects. The statement 'No browser is launched' is the only behavioral detail and is insufficient.

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

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

The description is only one sentence and is front-loaded, but it is not appropriately sized for a tool with nine parameters and no annotations. Its brevity omits critical information, making it under-specified rather than efficiently 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?

Given the high parameter count and lack of output schema, the description is far too minimal. It does not explain how the parameters relate to the URL check, what a successful or failed check returns, or the tool's overall behavior. The description is inadequate for an agent to use 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?

Although every parameter has a schema description, the descriptions are inconsistent with the tool's stated purpose. For example, 'url' is described as 'HTTPS URL to normalize or cite' rather than a URL to check, and many parameters are said to be 'discarded' without explaining their relevance. This adds confusion instead of meaning.

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 an action ('Check whether a URL can be opened') but does not clearly identify which parameter is the URL or how this differs from sibling tools like browser-url-ok or fetch-status. The presence of unrelated parameters such as 'ref', 'city', and 'zone' further muddles the tool's actual 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 given about when to choose this tool over alternatives like browser-url-ok or fetch-status. The only hint is 'No browser is launched,' which is a constraint but not a usage guideline.

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 that the query is discarded, which is a useful side-effect note. However, with no annotations provided, it leaves out behavioral details such as return format, failure modes, or behavior with empty input.

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, using only two short sentences. No unnecessary wording is present.

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 the concise description, the tool has nine parameters and no output schema. The description omits what the tool returns, how the extra parameters are handled, and edge-case behavior, leaving significant gaps for an agent trying to invoke 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?

Parameter descriptions exist and cover the schema, but most are confusing and seemingly unrelated to the tool's purpose (e.g., 'Git ref name; discarded after the shape check'). The description does not clarify why so many irrelevant parameters are accepted or how they relate to counting a search query.

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 characters in a search query, giving a specific verb and object. It does not explicitly differentiate from sibling tools, but the core purpose is unambiguous.

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

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

The description gives no guidance on when to use this tool versus alternatives such as normalize-url or validate-json. It only states what it does, not the conditions under which it should be selected.

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

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

With no annotations provided, the description carries the full burden of disclosing behavior. It only states that it is a 'catalog' but does not explain what happens when parameters are passed, whether it performs any validation, returns data, or has side effects. The schema notes that several parameters are 'discarded after the check', but the description does not clarify this.

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 in length, but it does not earn its place because it adds no actionable information. It is under-specification rather than efficient writing. The front-loaded content is merely a restatement of the tool's name.

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

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

Given 9 parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain how the tool uses the parameters, what it returns, or any constraints. An agent cannot determine correct invocation from 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?

Schema description coverage is 100%, so every parameter has a description in the schema. The tool description adds no additional meaning about parameters. According to the rubric, a baseline of 3 is appropriate when schema coverage is high, even if the description omits parameter details.

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 'Short catalog of common HTTP status codes' is a noun phrase that essentially restates the tool name 'status-catalog'. It lacks a verb indicating what action the tool performs (e.g., returns, lists, validates). It does not differentiate from sibling tools like 'fetch-status' or 'browser-url-ok', which also relate to HTTP statuses.

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 any of the 26 sibling tools. There is no mention of appropriate contexts, alternatives, or exclusions. An agent has no basis to select this tool over others.

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 gives no indication of side effects, permissions, or safety implications. It does not state whether the tool is read-only, destructive, or performs any external actions, and no annotations are available to fill this gap.

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

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

The description is concise in length but structurally poor; it provides no additional context or logical flow. It lacks a clear explanation of what the tool does beyond a bare statement, making it unhelpful despite its brevity.

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

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

The description is insufficient for an agent to understand the tool's context, including its expected inputs, outputs, or purpose. With no output schema or annotations, the description fails to provide the necessary background to correctly invoke the 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?

The schema provides descriptions for each parameter (e.g., 'url: HTTPS URL to normalize or cite'), but these descriptions seem disconnected from the tool's stated purpose of returning a thinking template. The description adds no clarification on how these parameters contribute to the tool's 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 'Return a three-step thinking template' is vague and does not clarify what the template contains or its use case. It fails to distinguish the tool from its siblings, and the parameters (url, city, query, etc.) are unrelated to the described purpose, causing confusion.

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 phrase 'Prompt discarded' is cryptic and offers no actionable direction for an agent deciding whether to invoke this tool.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention what happens with an invalid timezone, whether the tool performs any network call, whether it returns just the time or includes other data, or why the schema contains nine unrelated parameters (ref, url, city, feed, host, json, path, query) that appear irrelevant to timezone. This lack of disclosure makes the tool's behavior opaque and potentially misleading.

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 (a single sentence), which is positive, but it is under-specified for a tool with nine parameters. It is not front-loaded with the key parameter (zone) and provides no structure to help an agent understand the tool's actual scope. It earns a middle score for brevity but loses points for not using the space to clarify essential usage.

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 optional parameters, no annotations, no output schema), the description is severely incomplete. It does not explain the role of the extra parameters, does not specify the return format, and does not mention error behavior or edge cases. An agent cannot confidently determine how to invoke this tool correctly or what to expect from it.

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

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

Schema description coverage is 100% (all parameters have descriptions), so the baseline is 3. However, the description itself does not add any meaning beyond the schema. It does not highlight which parameter (likely 'zone') is the essential one, nor does it clarify that the other eight parameters are extraneous or ignored. The schema descriptions themselves are terse and offer no context for why they exist in a timezone tool, so the description fails to compensate for that confusion.

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: 'Current time in a named IANA timezone.' It uses a specific verb ('Current time') and resource ('IANA timezone'), which distinguishes it from the sibling 'utc-time' (which presumably returns UTC rather than a named zone). However, it does not explicitly mention the alternative, so it scores a 4 rather than 5.

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 like 'utc-time' or other time-related tools. It does not state any conditions, prerequisites, or exclusions. An agent is left to infer that this tool is for a named zone, but there is no explicit 'use this when' or 'use that instead' 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 of behavioral disclosure. Beyond stating it returns a timestamp, it does not disclose that all 9 parameters are effectively ignored (though the schema descriptions say they are discarded). It also does not indicate whether the tool makes network calls, is read-only, or has any side effects. The description is too thin to be behaviorally transparent.

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 clear sentence with no filler. It is appropriately concise and front-loaded with the essential information.

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

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

For a simple tool that returns a timestamp, the description is minimal but arguably sufficient. However, the presence of 9 optional parameters with unclear relevance to the stated purpose is not explained in the description. The schema descriptions cover each parameter, so the description does not need to repeat them, but the tool's odd interface could confuse an agent. Overall, it is adequate but not complete for a tool with such a complex input 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 description adds no parameter semantics beyond the schema, but the schema itself explains each parameter's role (e.g., 'discarded after the check'). The description does not need to compensate, so 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 tool returns the current UTC timestamp. This is a specific verb+resource, and the purpose is unambiguous. It is distinguished from siblings like timezone and iana-zones by the explicit 'UTC' qualifier.

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

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

The description provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, typical use cases, or exclusions. An agent would have to infer from the name alone when to prefer this over similar time-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?

The description does not disclose side effects, read-only nature, rate limits, or what happens with inputs. The parameter descriptions mention 'discarded after the call' but that is inconsistent and does not clarify 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 a single concise sentence that is easy to parse.

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?

An agent cannot determine how to call this tool correctly. It does not specify that only 'city' is needed, nor how to pass the city name. The extraneous parameters create confusion and the description fails to provide essential context.

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

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

The parameter descriptions are generic and unrelated to weather (e.g., 'ref' for Git ref, 'url' for HTTPS URL). The description adds no clarification on which parameters are actually used, making the set of 9 parameters misleading.

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's function: returning current temperature for a city via Open-Meteo. It distinguishes from sibling tools like geo-hint or timezone, but does not specify which parameters are relevant.

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 prerequisites or conditions. The description only states what it does.

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 phrase 'Title discarded after the call' hints at statelessness but does not clarify side effects, return values, or error behavior. Without annotations, this minimal note is insufficient for understanding the tool's full 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 very short and economical, but the mismatch between the stated purpose and the schema makes it less effective. It is not verbose, yet it fails to align with the input 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?

The description omits critical details such as the expected return value (e.g., boolean) and does not address the actual parameters. The mismatch with the schema leaves an agent without enough information to invoke the tool correctly.

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

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

The description implies a single 'title' parameter, but the schema lists nine unrelated parameters (ref, url, city, etc.) with generic descriptions. The description adds no meaning to the actual parameters and contradicts the schema's parameter list.

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 and resource: 'Check whether a Wikipedia title exists.' This distinguishes it from sibling tools like browser-url-ok or file-path-ok, though the schema does not contain a 'title' parameter.

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

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

No guidance is provided on when to use this tool versus alternatives such as search-query-len or normalize-url. The description does not mention any conditions or context that would direct an agent to pick this tool.

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