Language mr

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

With no annotations, the description carries the behavioral burden. It does disclose that 'Task text is discarded.' and that the tool 'Returns connection methods,' which suggests a read-only catalog lookup. However, it does not explain whether the call is network-bound, whether using a returned gateway has cost implications, or what failure/response behavior looks like.

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 with the tool's purpose and use cases, making it efficient. The phrase 'Task text discarded.' is somewhat ambiguous given there is no task-text parameter in the schema, which keeps this from being a perfect 5.

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 a rich 9-parameter schema with per-parameter descriptions, the tool has no output schema, no annotations, and a task-finding job that is underspecified for an agent. It never explains how to map a task like 'voice' or 'scrape' onto the listed parameters (host, feed, json, path, zone), nor what 'connection methods' actually contains, leaving a substantial invocation gap.

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 every parameter, yielding a baseline of 3. The description's mapped task categories ('weather, search, scrape, voice') loosely hint at which parameter groups matter, but it does not explicitly tie parameters to the advertised tasks or add further semantics.

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

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

The description states a specific verb and resource: 'Find a public pay-per-call tool gateway,' with concrete example tasks ('weather, search, scrape, or voice'). This clearly distinguishes the tool from the narrower sibling utilities (e.g., weather-hint, timezone, normalize-url), which operate on single domains. The added 'Task text discarded' detail also sharpens the tool's scope.

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

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

The description implies when to use the tool through examples ('for a task such as weather, search, scrape, or voice'), but it does not explicitly state alternatives or when not to use this tool versus the sibling utilities. No exclusions or comparison routes are given, so guidance is left mostly 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?

No annotations exist, so the description carries the full burden of behavioral disclosure. It does disclose that no browser is launched, which is a useful side-effect note, but it omits what the tool actually does with the parameters, what it returns, or any side effects or side-effect-free guarantees for the other fields.

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 short sentence, which is under-specified rather than concise. It fails to describe the tool's behavior across its heterogeneous parameter set, and the single sentence does not earn its place because it doesn't aid correct invocation.

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

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

With nine parameters, a vague one-line description, no output schema, and no annotations, the definition is grossly inadequate. An agent has no way to know what inputs are needed, what outcome to expect, or how this tool differs from its many siblings. This is a severe completeness gap.

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 schema coverage is 100%, the description adds no semantic link between the stated purpose and the nine parameters. The parameter descriptions themselves are self-contained but do not explain how they relate to 'checking whether a URL can be opened.' An agent cannot infer which parameter(s) drive the check or how the others contribute.

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 and resource ('check whether a URL can be opened'), which is specific, but it conflicts with the parameter set: the schema includes city, zone, json, path, query, etc., which have nothing to do with URL openability. This makes the actual purpose ambiguous and likely misleading for an agent.

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 sibling tools like normalize-url, fetch-status, or web-fetch. The description gives no context, prerequisites, or exclusions, leaving the agent to guess which tool applies.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'Expression discarded' but there is no expression parameter, and it does not describe any side effects, return behavior, restrictions, or requirements. The description is actively uninformative 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 extremely short (one sentence), but conciseness without substance is under-specification. It omits essential information about the 9 parameters and the tool's operation, so it does not earn 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?

Given the tool's complexity (9 parameters, no output schema, no annotations), the description is profoundly inadequate. It could not enable an agent to call the tool correctly or understand its behavior, and it fails to cover any of the parameter semantics or intended use.

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 tool description adds no value for the parameters. It does not relate 'a+b style arithmetic' to any of the documented parameters, nor does it explain how they are used or discarded. The description is disconnected from the schema and fails to enhance parameter understanding.

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

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

The description claims 'Evaluate a+b style arithmetic' but the input schema contains parameters like ref, url, city, feed, host, json, path, zone, and query—none of which are arithmetic expressions. This is misleading and fails to state what the tool actually does with these parameters or how it distinguishes from siblings.

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 or when to prefer a sibling. It offers no context about use cases, exclusions, or alternatives, leaving the agent without any 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?

No annotations exist, so the description must carry the behavioral disclosure burden. It only states that page content is not stored, but fails to explain the fate of the other 8 parameters (e.g., 'discarded' hints are in the schema, not the description) or any side effects, permissions, or rate limits.

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

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

A single, front-loaded sentence that presents the core purpose immediately. It is concise and avoids filler, but the brevity sacrifices necessary context for the broader 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, and no annotations, the one-line description is grossly insufficient. It covers only the URL-centric function while ignoring the other 8 parameters that appear to be validated or discarded. An agent cannot reliably infer how to invoke the tool for the non-URL cases.

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%—every parameter has a description in the schema. The tool description adds no meaning beyond the schema; it only implicitly references the 'url' parameter. Given the high schema coverage, a baseline 3 is appropriate.

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

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

The description states a specific verb ('Return') and resource ('host, scheme, and HTTP status for a URL'), which is clear for the URL-citation case. However, it does not differentiate from siblings like fetch-status or normalize-url, and the input schema includes many unrelated parameters (city, feed, json, path, zone, query) that muddy the tool's actual scope.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or hints about which sibling tools might be more appropriate for specific tasks.

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 contributes one useful trait — "No identifiers are retained" — which is a genuine privacy/retention guarantee. However, the per-parameter "discarded after" notes live in the schema, not the description, so the description itself discloses only retention behavior and nothing about the classification logic or output. Minimal but non-zero value.

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 zero waste, and the primary purpose is front-loaded ahead of the secondary privacy note. The structure is efficient, even if the content is thin.

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

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

A tool with 9 heterogeneous parameters (git refs, URLs, cities, RSS feeds, JSON, file paths, timezones, search text), no output schema, and no annotations is seriously under-described by two sentences. The description never clarifies what "classification" means, what the result looks like, or how the disparate inputs feed into a single compatibility verdict. Substantially more context 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?

Schema description coverage is 100%, so the baseline of 3 applies. Every one of the 9 parameters is already documented with field-specific notes (e.g., "Git ref name; discarded after the shape check"). The description adds nothing about how the parameters relate to the classification, so it provides no 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?

"Show how this request is classified" is vague — the noun "request" is never defined, and "classified" is never explained. The description never mentions compatibility, which is the tool's name and likely its core purpose, and it fails to differentiate from the many sibling validation tools (domain-shape, file-path-ok, validate-json, normalize-url). The verb+object structure exists but the object is too underspecified to direct an agent.

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

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

There is no when-to-use or when-not-to-use guidance. With 29 siblings spanning validation, normalization, and status-checking, an agent has no signal about which one to pick for, say, a URL shape check versus a generic compatibility classification. No alternatives are named and no exclusions are given.

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

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

Annotations are not provided, so the description carries the full burden of behavioral disclosure. It reveals side-effect/no-side-info by saying 'without WHOIS or ownership', but it does not state whether the tool is read-only, what happens to each input, how labels are returned, or what happens if the hostname is invalid.

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 one short, front-loaded sentence with no filler. The negative clause is purposeful and makes the tool scope clearer without causing verbosity.

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

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

Given the complexity of a nine-parameter tool with no annotations and no output schema, one sentence is not enough. The description explains the primary domain but doesn't map the other inputs described in the schema, nor does it elaborate the output shape that is so critical when no output schema is provided.

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 description coverage is 100%, so the baseline is 3 even without extra parameter detail from the description. The description does not map to schema specificity, relying on 'host' to need 'hostname', and does not explain why the schema exposes unrelated params (ref, json, zone, query). Because the schema is self-describing, the missing param refinement doesn't simplify the agent's command surface.

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 concrete action ('split a hostname into labels') and adds a scope constraint ('without WHOIS or ownership data'). However, with a hostname-focused purpose, the schema's nine heterogeneous optional parameters fight the same domain, so an agent has no clear image of what inputs this tool actually accepts.

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 when-to-use/when-not-to-use guidance and does not mention any sibling or alternative tool. The only cue is the negative 'without WHOIS or ownership data', which is a behavior on cases rather than a selector; the agent gets no comparison to normalize-url, browser-url-ok, or fetch-status.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions HEAD and status return, but does not explain what happens when other parameters are supplied, whether any side effects occur, or how the tool behaves for non-URL inputs. The schema's note 'no disk access' for path hints at safety, but the description adds no depth about the tool's actual execution or limitations.

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, front-loading the primary URL-focused purpose. However, for a tool with 9 parameters and multiple apparent functions, this is under-specified rather than efficiently complete. It lacks any structure to convey the tool's broader scope, making it feel inadequate rather than appropriately sized.

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

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

Given the tool's complexity (9 parameters, no output schema, no annotations), the description is far from complete. It does not explain the tool's behavior for the majority of parameters, nor does it provide any context on return values, error handling, or prerequisites. An agent would not be able to correctly invoke this tool for non-URL use cases based on the 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 the schema already documents each parameter. The description adds no additional semantic meaning about how parameters interact, which parameter is primary, or what the tool does when multiple parameters are provided. This matches the baseline of 3 for high schema coverage.

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

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

The description states a specific verb and resource (HEAD a public URL) and a clear outcome (status only), which is not a tautology. However, the input schema accepts 9 unrelated parameters (ref, city, feed, zone, etc.), so the description only covers one of several apparent capabilities. This makes the tool's full purpose ambiguous and could mislead an agent into thinking it only handles URLs when it also handles timezones, weather hints, validation, and more.

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 its siblings such as browser-url-ok, playwright-url-ok, or web-fetch. There is no mention of alternatives, exclusions, or context that would help an agent choose this tool. The presence of many sibling tools with overlapping URL-checking roles makes this gap significant.

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

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

No annotations are provided, so the description carries the full burden. It only states that the path is discarded, which is a minor behavior. It does not explain whether the URL is mutated, what format the output takes, whether network access is involved, or any side effects. This is minimal disclosure for a tool that appears to both parse and validate.

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—two short sentences with no filler. The main action is front-loaded, and the discarded-path detail is clear. Every word earns its place.

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

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

For a tool with 9 parameters, no output schema, and no annotations, this description is severely incomplete. It gives no indication of what the tool returns, how to combine parameters, or what 'parse' means in practice. The parameters include many unrelated fields (city, feed, zone, json) that seem inconsistent with a Figma URL parser, and the description does nothing to resolve that ambiguity.

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 each parameter is documented in the schema. The description adds no additional meaning about how parameters like 'city', 'feed', or 'zone' relate to parsing a Figma URL, which is puzzling. However, since the schema fully describes each parameter, the baseline of 3 applies; the description contributes nothing beyond it.

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 parses a Figma file URL, which is specific and matches the tool name. The 'Path discarded' note adds a small detail. However, it doesn't differentiate from sibling URL tools like 'normalize-url' or 'browser-url-ok', so it's not a 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?

There is no guidance on when to use this tool versus alternatives. With 28 sibling tools including several URL-related ones, an agent has no indication of when 'figma-url-shape' is preferred. No context about prerequisites, limitations, or excluded scenarios.

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

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

With no annotations, the description carries the full behavioral burden. The explicit 'No disk access' is valuable and clarifies a non-side-effecting trait. However, it doesn't state return behavior, validation thresholds, or how it treats the various optional parameters, leaving important behavioral 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 exceptionally concise: one purpose sentence and one behavioral qualifier, both front-loaded with zero filler. Every word earns its place, and the structure is easy to scan.

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

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

For a tool with 9 optional parameters, no required fields, and no output schema, the description is severely incomplete. It does not explain expected input patterns, what constitutes a 'safe' path, return values, or error behavior. An agent cannot reliably call it correctly without inspecting the schema and making assumptions.

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

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

Schema coverage is 100%, so each of the 9 parameters has an individual description in the schema. The tool description adds no additional meaning beyond the word 'path', and it fails to clarify why the schema contains unrelated parameters like city, zone, and query. Baseline 3 is appropriate because the schema carries the semantics, but the description offers no extra value.

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

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

The description states a clear verb and resource ('Check whether a path looks safe'), and the second sentence adds a distinguishing safety property ('No disk access') that separates it from side-effecting tools. However, it doesn't explain what 'safe' means or how it differs from sibling shape-checking tools beyond the path focus.

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

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

There is no guidance on when to use this tool versus alternatives like browser-url-ok or domain-shape. No prerequisites, exclusions, or context about expected call scenarios are given; the single sentence implies a purpose but offers no 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?

No annotations are provided, so the description carries the full burden. It states the tool returns lat/long but does not disclose behavioral traits such as that inputs are discarded, that it calls an external service, or any side effects. The schema mentions 'discarded after the...' for many parameters, but the description does not surface this, leaving behavioral transparency inadequate.

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

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

The description is concise (a single sentence) and not verbose. However, it lacks structure—no front-loading of key caveats or usage context. It is minimal but not misleading; it earns a middling score for simplicity without offensive verbosity.

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

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

The tool has 9 optional parameters and no output schema. The description provides no information about return format, expected city format, or how the parameters map to the geocoding task. It is completely inadequate for an agent to confidently invoke the tool. The mismatch between description and schema makes it nearly 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?

Though the schema has 100% description coverage, the descriptions are misleading. For example, 'city' is described as 'for a public weather hint; discarded after the call'—not as a place to geocode. Other parameters are entirely unrelated to the tool's stated purpose. The descriptions do not help an agent understand how to construct a valid call, failing to add meaningful semantics 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 a clear purpose: 'Latitude and longitude for a place via Open-Meteo.' It uses a specific verb and resource. However, the input schema does not align with this purpose; the parameters (e.g., 'ref', 'url', 'host') are unrelated, and the only plausible one, 'city', is described as 'for a public weather hint' not for geocoding. This inconsistency weakens clarity and does not distinguish the tool from siblings like 'weather-hint'.

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

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

No guidance is provided on when to use this tool versus alternatives. The description merely states what it does, without mentioning any applicable scenario, constraints, or alternative tools. The presence of sibling 'weather-hint' suggests a potential overlap, but no differentiation is 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?

With no annotations provided, the description carries the full burden but only states the core parsing intent. It does not disclose output format, invalid-URL handling, validation behavior, or side effects.

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

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

The description is a single, front-loaded sentence with no redundant wording or filler.

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 gives only the basic purpose but omits essential context: which of the nine optional parameters are actually used, the expected output shape, error behavior, and why the unrelated parameters appear.

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 url parameter is described as 'HTTPS URL to normalize or cite' rather than a GitHub URL to parse, and eight extraneous optional parameters with unrelated or misleading descriptions are included. This actively misleads rather than clarifies the actual parameter usage.

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 ('parse'), names the resource ('GitHub URL'), and states the output ('owner and repo'), which distinguishes it from other shape or URL 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 about when to use this tool versus siblings like normalize-url, domain-shape, or figma-url-shape, and no exclusions or preferred input conditions are mentioned.

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

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

There are no annotations, so the description carries the full burden of behavior. It discloses only that titles are discarded, but does not say whether the tool is read-only, whether it fetches external data, how the 9 parameters behave, or what error cases exist.

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 short sentences, uses no fluff, and puts the purpose first. 'Titles discarded' is terse almost to the point of opacity, but the overall message is efficient.

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

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

The tool has 9 parameters, no output schema, and no annotations, and the description is only 9 words. It fails to clarify the output format, the relationship between the parameters and the HN front page count, or any usage constraints. This is not complete enough for an agent to invoke it correctly without significant guesswork.

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

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

The schema provides descriptions for all 9 parameters (100% coverage), so by the rubric the baseline is 3. But the description itself adds no meaning about which parameters, if any, affect the count; the parameter list looks unrelated to 'Hacker News', so an agent cannot tell which inputs matter despite the schema detail.

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 ('Count') and resource ('current Hacker News front-page stories'), and adds a behavioral qualifier ('Titles discarded'). It is more than a tautology, though it mostly glues the cryptic name into a sentence.

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 any of the 29 siblings, no exclusions are mentioned, and conditions are never stated. The only inference is through the name, which the agent could already make.

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

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

With no annotations provided, the description must fully disclose behavioral traits, but it reveals nothing about side effects, return values, error handling, or state changes. The schema hints that many parameters are 'discarded after' checks, implying validation behavior, but the description does not clarify this. No behavioral contract is communicated.

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

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

The single sentence is minimal, but it is under-specified rather than concise. It omits critical information, and the lack of structure (e.g., bulleted usage, parameter context) makes it unhelpful. Conciseness should not come at the expense of necessary 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?

Given the tool has 9 parameters, no output schema, and no annotations, a complete description is essential. This description provides almost no context: it does not explain why the parameters are present, what the tool returns, or how it fits into a workflow. It is wholly inadequate 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?

Although schema_description_coverage is 100%, the description adds no meaning to the parameters. The nine parameters (ref, url, city, feed, host, json, path, zone, query) are diverse and unrelated to the stated purpose of 'IANA timezone names.' The description does not explain how these parameters are used or why they are relevant, leaving the agent to infer from field names alone.

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

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

The description 'Common IANA timezone names for clock calls' names a resource (timezone names) and a domain (clock calls) but never states what action the tool performs—does it list, validate, or resolve names? It does not distinguish itself from sibling tools like `timezone`, `utc-time`, or `weather-hint`, all of which are time-related but have clearer purposes.

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 guidance is provided. There is no statement about when to invoke this tool, when not to use it, or how it relates to alternatives such as `timezone` or `utc-time`. An agent would have no basis to select this tool over its siblings.

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

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

There are no annotations on this tool, so the description carries the full behavioral disclosure burden. It says the fetch is public and that only group counts are returned, but it does not disclose what happens with inaccessible or non-public URLs, whether values are ignored, or how failures or malformed robots.txt files are handled.

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

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

The description is one compact sentence with no filler. It front-loads the action and the output restriction, making it easy to read and immediately actionable.

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, yet the description only gives a high-level purpose. It does not clarify which parameter supplies the robots.txt URL or what shape the returned group counts take, so an agent would struggle to invoke it confidently from the 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?

Since the schema has 100% parameter description coverage, the baseline is 3. The description does not add meaning beyond the schema; it also does not say which of the nine parameters is the robots.txt URL or how the unrelated-looking optional parameters such as city, zone, and json relate to the tool's behavior.

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

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

The description names a specific verb and resource: fetch a public robots.txt and return only group counts. This is distinct from every sibling tool listed, none of which is about robots.txt or group counts, so an agent can clearly tell what this tool does.

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

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

The description provides no guidance on when to use this tool instead of alternatives like web-fetch or normalize-url, and it states no exclusions or when-not-to-use conditions. The only usage signal is implied from the resource name and the verb.

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

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

With no annotations, the description must bear the full burden of behavioral transparency. It only says the key is discarded and the shape is checked. It does not disclose what happens on success or failure, whether any side effects occur, or what return value the agent should expect.

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

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

The description is very concise and front-loaded with the core action, but it is too terse for the complexity of the tool. The second sentence ('Key discarded.') adds minimal detail, and the overall brevity leaves out critical invocation and behavior 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?

Given 9 parameters, no required fields, no output schema, and no annotations, the description is far from complete. It does not specify which input to use, what return value to expect, how errors are handled, or how the tool fits into a larger workflow. An agent would be unable to reliably invoke this tool based solely on the 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?

Although all 9 parameters have schema descriptions (100% coverage), those descriptions are unrelated to a Jira issue key (e.g., 'Git ref name', 'IANA timezone name'). The tool description does not explain which parameter should hold the Jira key, so the schema and description fail to map inputs to the tool's actual purpose.

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

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

The description states a specific action ('Check') and a specific object ('Jira issue key shape'), which makes the tool's purpose clear and distinguishes it from sibling shape-checking tools like domain-shape or github-repo-shape. It loses one point because it does not explicitly name an alternative or clarify which input parameter should contain the Jira key.

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

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

No usage guidance is provided. The description does not say when to use this tool versus other shape-checking tools, nor does it give context such as 'use to validate a Jira key before an API call.' The purpose is implied but not explicitly connected to any workflow.

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 full responsibility for disclosing behavior. It reveals nothing about side effects, output, permissions, or limitations. The parameter descriptions hint at some kind of shape check or validation, but the tool description does not confirm or explain this 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 short phrase, but this is under-specification rather than conciseness. It conveys almost no information and does not earn its place as a tool description. A good concise description would still be informative; this one is merely terse.

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

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

For a tool with 9 optional parameters and no output schema, the description is grossly inadequate. It does not explain the tool's purpose, the relationship between the parameters, or what result an agent should expect. The sibling context suggests a family of checkers, but nothing here tells an agent how to use this tool correctly.

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

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

The schema covers 100% of parameters with descriptions that indicate how each input is used (e.g., 'discarded after the shape check'). Since schema coverage is full, the baseline is 3. The tool description itself adds no meaning, but the schema descriptions provide some semantics, so the description does not need to repeat them. However, the description's failure to contextualize these parameters keeps 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 'ISO 639 language tag mr.' is a noun phrase that restates the tool name without stating any action. It does not mention what the tool does (e.g., validate, lookup, or generate a language tag) and provides no verb or resource beyond the language code itself. It is essentially a tautology and fails to distinguish the tool from its many sibling checkers.

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 28 siblings. No context, no exclusions, no mention of alternatives. An agent has no idea what scenarios would call for lang-mr or how it relates to tools like wiki-title-ok or validate-json.

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

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

With no annotations, the description must carry the full behavioral burden. It discloses 'Body discarded', which is useful, but it does not explain how the other eight parameters are used, whether it follows redirects, or any error behavior. The multi-purpose nature of the tool is completely opaque, so an agent cannot anticipate its side effects or scope.

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

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

The description is a single sentence with no wasted words, and the core action is front-loaded. It is appropriately concise for its length, though it may be too short for the tool's complexity.

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

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

Given the tool has 9 parameters and no output schema, the description is grossly insufficient. It only covers one narrow scenario (URL status) and gives no hints about the other parameters, return format, or edge cases. An agent would be completely lost about how to use this tool for non-URL inputs.

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. However, the description only references 'URL' while ignoring the other eight parameters. It adds no meaning beyond the schema and actually misleads by implying the tool only deals with URLs, not with weather, timezones, JSON validation, etc.

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

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

The description states a specific verb and resource ('HTTP status for a public library docs URL'), but the tool accepts nine unrelated parameters (city, zone, json, etc.) that the description ignores. This makes the actual purpose ambiguous and fails to distinguish it from siblings like fetch-status or browser-url-ok, which likely also return HTTP status.

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

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

No guidance is given on when to use this tool versus alternatives. There is no mention of trade-offs like speed, body discarding as a differentiator, or when a full fetch is needed. The description simply states what it does without any contextual routing.

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 responsibility of behavioral disclosure, but it only says 'Values discarded.' It does not reveal side effects, whether it reads persistent memory, whether nested keys are counted, or what the operation actually affects.

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 extremely concise and front-loaded: 'Count keys in a JSON object.' The second sentence adds a useful fact, and there is no filler. It loses a point because it is so short that it omits essential operational 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?

The tool has 9 optional parameters, no annotations, no output schema, and no explicit operating instruction. The description does not explain how to invoke the tool with a JSON object, how depth is handled, or whether a specific parameter like 'json' is required, so the definition is insufficient on its own.

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 descriptions cover 100% of parameters, and each parameter already explains its meaning, so the baseline is 3. The tool description adds no extra parameter-level guidance about which parameter is the JSON object to inspect, but the schema's own descriptions help fill that gap.

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

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

The description states a clear verb ('Count') and a resource ('keys in a JSON object'), so it goes beyond a tautology. However, it doesn't specify which of the 9 optional parameters carries that JSON object, leaving the agent to guess between 'json' and other unrelated parameters.

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

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

No guidance is provided on when to use this tool, what conditions select it, or how it compares to siblings like validate-json or other shape-check tools. The usage context must be fully inferred by the model.

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

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

With no annotations, the description carries the full behavioral disclosure burden. It does disclose that query and fragment are dropped, but it says nothing about whether this is a local-only operation, whether it performs network/disk access, whether it has side effects, or how invalid URLs are handled.

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

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

The description is short, front-loaded, and contains no filler. The first sentence gives the core action and output, and the second adds a relevant transformational detail. For what it covers, it is appropriately compact.

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

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

The tool has 9 optional parameters, no annotations, and no output schema. The description does not say which parameter to pass, whether all other parameters are ignored, what the returned value looks like, or how errors are reported, making it incomplete for reliable selection/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 schema carries the parameter meaning. The description adds the URL-level behavior of dropping query and fragment, but it does not clarify that the 9 optional parameters are mostly discarded or that only the 'url' field is the actual target of the operation.

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 concrete verb and resource: return origin, host, and path for a URL. It also adds the query-and-fragment dropping behavior, which helps distinguish it from URL fetch/status siblings. It does not explicitly contrast those siblings, so it is clear but not maximally differentiated.

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 browser-url-ok, web-fetch, citation, or other URL-related siblings. The description does not state prerequisites, exclusions, or when NOT to use it, so an agent must guess from the name and friend tool list.

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 full responsibility. It does disclose one behavioral trait ('No browser is launched'), but this is contradictory to the promised 'can be opened' and lacks details on side effects (e.g., does it make a network request?), error handling, or what 'ok' means. The agent cannot predict the tool's behavior reliably.

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

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

The description is extremely concise (one sentence), which is efficient, but it lacks essential information. It is not front-loaded with the most critical detail (what constitutes 'ok'), and the brevity comes at the cost of clarity.

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

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

For a tool with 9 optional parameters, no required ones, and no output schema, the description is grossly inadequate. An agent cannot determine what input to provide, what the tool returns, or what side effects occur. The description fails to compensate for the complexity of 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%, so each parameter has a brief description. However, the tool description adds no guidance on which parameter to use or how they relate to the stated purpose. The parameters are all optional and cover diverse domains (URL, city, JSON, path), so the schema alone is insufficient for selecting the right 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 states a verb and resource ('check whether a URL can be opened') but immediately contradicts it with 'No browser is launched,' leaving the actual mechanism unclear. It doesn't distinguish from siblings like browser-url-ok or normalize-url, and the presence of many unrelated parameters (city, zone, json) suggests a broader purpose than URL checking, which is not conveyed.

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 such as browser-url-ok, normalize-url, or fetch-status. There are no conditions, exclusions, or context hints, leaving the agent to guess when this tool is appropriate.

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

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

With no annotations, the description carries the full burden. It discloses that the query is discarded, which is a privacy-related behavior. However, it does not state the return value or any other side effects. For a simple counting tool, the description is mildly informative but lacks completeness.

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—two short sentences with no filler. The core action is front-loaded, and the behavioral note about discarding is included. Every word earns its place.

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 has 9 optional parameters, no output schema, and no annotations, the description is far too sparse. It doesn't explain what the tool returns, how to interpret the result, or how it fits among 28 siblings. An agent would struggle to know when to invoke this tool and what to do with the output.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds no extra meaning about any parameter; it doesn't even explicitly identify which parameter is used for the query. The schema already documents each parameter's purpose, so the description provides no added value.

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

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

The description states a specific action (count characters) and the resource (a search query). It is clear but does not differentiate from sibling tools like memory-key-count or hn-front-count. Given the tool name already implies the purpose, the description adds a bit of clarity but not enough for selection among siblings.

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 exclusions or prerequisites. The description is silent on context, leaving the agent to infer usage from the name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It fails entirely – it doesn't mention what happens to inputs, what operations are performed, what the output looks like, or any side effects. The parameter descriptions in the schema hint at discarded values, but the tool description itself offers zero 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 vague sentence that under-specifies the tool. It is short but not effective – it fails to front-load any useful content. The sentence does not earn its place because it merely restates the obvious and omits critical 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?

Given the tool's complexity (9 parameters, many siblings, no output schema), the description is completely inadequate. It doesn't explain the tool's purpose, usage, or output, leaving an agent unable to correctly invoke it for any task.

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 even though the description adds no parameter information. The schema itself provides useful descriptions (e.g., 'discarded after the shape check'), but the tool description adds nothing to clarify how the parameters relate to generating or cataloging status codes.

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 'Short catalog of common HTTP status codes,' which restates the tool name and offers a vague noun phrase rather than a clear verb+resource. It does not explain what the tool does with the 9 input parameters, so an agent cannot infer its function or distinguish it from siblings like fetch-status or 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 on when to use this tool vs. alternatives. The description gives no context, prerequisites, or exclusions. An agent has no way to decide between status-catalog and the related 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 discloses that the prompt is discarded, but does not explain that the nine parameters are also effectively ignored (beyond a shape/length check) and that the output is identical regardless of input values. The schema notes 'discarded after...' for several parameters, but the description does not clarify this behavior, potentially misleading the agent into thinking inputs affect the template.

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 (one sentence), but this is under-specification rather than appropriate conciseness. It lacks critical details about the template and parameter handling. While it is front-loaded with the core action, the brevity comes at the expense of essential context, making it ineffective.

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 optional parameters, no output schema, and no annotations, the description is woefully incomplete. It does not explain what the three-step template contains, what the parameters are for, how the input is used, or what the return value looks like. An agent has no way to format a call or interpret the result 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 the schema has 100% description coverage, the tool description adds no meaning about parameters. The schema entries are inconsistent (e.g., 'url' implies normalization/citation, 'city' implies a weather hint, but the tool is supposed to return a static template). The description does not resolve these contradictions, so an agent cannot determine whether providing parameters is useful or redundant.

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

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

The description states a clear verb and resource: 'Return a three-step thinking template.' It is distinct from siblings in that it yields a static template rather than performing a data operation. However, it does not describe what the three steps are, leaving ambiguity about the actual output. The phrase 'Prompt discarded' adds a hint that input is ignored, but the purpose remains somewhat vague.

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

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

No guidance is given on when to use this tool versus alternatives. There is no mention of eligibility conditions, when it should be preferred, or any exclusions. The description does not help an agent decide to call this tool over any other, leaving the decision to inference from the name.

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

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

With no annotations, the description bears full responsibility for disclosing behavior. It only states the output ('current time') and does not mention return format, error handling for invalid zones, whether a network or system clock is consulted, or that all non-zone parameters are ignored. This is a minimal disclosure that leaves important behavioral traits unstated.

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 eight-word sentence with no filler or redundancies. It is appropriately sized for a tool of this simplicity and front-loads 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?

Given the nine optional parameters and the absence of an output schema, the description is incomplete. It does not tell the agent that only 'zone' is relevant, nor does it describe what the returned time looks like. The agent must reason from the schema to determine the correct call, which is unnecessarily ambiguous.

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 already provides 100% coverage, describing 'zone' as 'IANA timezone name' and other parameters as discarded. The tool description merely restates the zone concept without adding guidance about which of the nine optional parameters to use. It adds no semantic 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 clearly identifies the tool's function: return the current time for a given IANA timezone. This distinguishes it from siblings like utc-time (presumably UTC-only) and iana-zones (listing zones). It is not a tautology and conveys the core operation, though it lacks a verb like 'get' or 'return'.

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 'named IANA timezone' implies when to use the tool, but there is no explicit guidance on when not to use it or how it compares to alternatives such as utc-time. The agent must infer the use case from the description alone, with no exclusions or alternative routing.

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

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

Annotations are absent, so the description carries the full burden of behavioral disclosure. It is silent about the 9 parameters being discarded/no-ops, silent about the lack of side effects, and silent about the output format. An agent reading only this description would not know that passing all parameters has no effect.

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 six-word description is compact and front-loaded with its single idea. It is too terse for the actual contract, though — a second sentence noting that input parameters are discarded would have been low-cost and materially more useful.

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, so the absence of a return-format statement (e.g., ISO-8601 vs. RFC 3339 vs. epoch) leaves a real gap. The decoy parameter set is not acknowledged anywhere in the text, and the lack of guidance around it makes the definition incomplete for a tool that in practice requires no arguments.

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 of 3 applies. The description adds nothing about the parameters beyond what the schema says, though it also doesn't lead to confusion by repeating or contradicting 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 names the exact resource ('UTC time') and is unambiguous about what is being provided. However, it is a bare noun phrase with no verb, and it does not differentiate from the sibling tools 'timezone' and 'iana-zones', so an agent may not know which of those to select.

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. Given the sibling 'timezone' and 'iana-zones', a statement about when UTC-now is necessary versus when timezone data is needed would be valuable; nothing like that appears.

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 fully disclose behavior. It states that 'The body is discarded,' implying a read-only, side-effect-free operation, which is helpful. However, it does not mention whether the tool performs network access, validates against a schema, or how it reports results (e.g., boolean vs. error), leaving significant 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 two sentences are extremely concise and front-loaded, with the purpose stated first and the discard behavior second. Every word earns its place, and no fluff or redundant phrasing exists.

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

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

For a tool with 9 parameters, no output schema, and no annotations, the description is incomplete. It fails to clarify that only the 'json' parameter is relevant, what constitutes 'valid JSON' (syntax only or structural), or the return format. Agents could easily misapply it, and the mismatch between 'body' and the 'json' parameter adds confusion.

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 documents all 9 parameters, including that 'json' is the text to validate. The description adds no extra value to parameter meaning; in fact, it introduces ambiguity by using 'body' instead of 'json.' The baseline of 3 applies, as the schema carries the semantic weight.

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

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

The description states a clear verb ('Check') and resource ('body is valid JSON'), which identifies the tool's primary function. However, it does not differentiate from sibling shape-checking tools like 'compatibility' or 'domain-shape', and it refers to 'body' while the schema parameter is 'json', which could cause minor 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 its many siblings. The description gives no context about typical use cases, prerequisites, or alternatives, leaving the agent to infer the tool's role from its name alone.

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

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

With no annotations, the description carries the full burden of behavioral disclosure, but it only states the outcome and API source. It does not disclose side effects, ignored parameters, output shape, or any prerequisites like API keys.

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 with no filler, front-loading the core functionality and provider. It is appropriately concise for a simple read-only weather lookup.

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 simple core function, the tool has 9 optional parameters and no output schema or annotations, so the description must clarify which field to use and what to expect. It does neither, leaving the agent to rely solely on the schema for a structurally confusing 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 each parameter is already documented. The description adds only minimal value by tying 'city' to temperature lookup, but does not clarify the roles of the other 8 parameters.

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 a city's current temperature via Open-Meteo, identifying both the resource and the data source. It distinguishes weather-hint from siblings like geo-hint or timezone, though it ignores the large unrelated input schema which slightly muddies the purpose.

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

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

No guidance is provided on when to use this tool versus alternatives, or on how to choose among the 9 optional parameters. The description only says what the tool does, leaving the agent to infer that 'city' is the operative parameter.

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 alone must convey behavioral traits. It discloses that the body is discarded and implies public URLs need no auth, but it fails to mention error handling, output format, rate limits, or side effects. For a tool with 9 parameters, this is minimal disclosure.

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

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

The description is a single clear sentence with no filler. The core result and key behavioral note (body discarded) are front-loaded. Every word earns its place.

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 annotations, and no output schema, the description is severely incomplete. It does not explain how the parameters relate to the reported output, which parameter is the primary URL, what the response structure looks like, or any constraints beyond 'public URL'. An agent would struggle to know how to invoke this correctly.

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

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

Schema coverage is 100%, and each parameter has a descriptive comment in the schema (e.g., 'Git ref name; discarded after the shape check'). The tool description adds no parameter-specific information beyond the schema, so it lands at the baseline for high coverage.

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

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

The description clearly states the action ('HTTP status and content type') and resource ('for a public URL'), and adds that the body is discarded. It is specific and not a tautology. However, it does not differentiate from the many sibling tools like fetch-status or browser-url-ok, so it loses one point.

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 does not mention any conditions, prerequisites, or explicitly name sibling tools for comparison. An agent is left without context for choosing this over similar URL-checking 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 of behavioral disclosure. It only states that the title is discarded after the call, which is a data-handling note, but it does not explain network access, rate limits, or side effects. The tool's actual behavior (e.g., how it checks Wikipedia) is opaque. The statement also seems inconsistent with the schema, as no 'title' 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 a single sentence, which is concise and front-loaded with the main action. However, it is too terse to convey the complexity of a tool with 9 optional parameters and no required ones. The sentence is not misleading but under-specifies the tool's scope, so it earns a middling score.

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

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

Given the high complexity (9 parameters, none required, no output schema), the description is grossly incomplete. It does not explain the role of each parameter, how the tool determines if a title exists, or what the output looks like. An agent cannot confidently invoke this tool based on the description alone. The description is inadequate for the tool's complexity.

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 description coverage is 100%, so each parameter has a description. The tool description adds no additional meaning about the parameters—it does not indicate which parameters are relevant to the title check or how they map to the functionality. Baseline 3 applies because the schema does the heavy lifting, but the description fails to clarify the relationship between parameters and 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 a specific verb and resource: 'Check whether a Wikipedia title exists.' It names the action and the object. However, it does not differentiate from sibling tools like 'browser-url-ok' or 'domain-shape' explicitly, and the mention of 'title' conflicts with the schema that has no 'title' parameter, which may confuse agents. The purpose is clear but not fully disambiguated.

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 are no context cues, exclusions, or references to sibling tools. An agent has no basis to choose this over a more specific tool like 'fetch-status' or 'normalize-url'.

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