Stone to pounds

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

There are no annotations, and the description only says 'Task text discarded' and mentions parameters being discarded. It does not disclose whether the tool makes network calls, requires authentication, has side effects, or incurs costs, so the behavior is not transparent enough.

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

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

The description is brief and front-loaded with the main purpose, and the parameter list is compact. The phrase 'Task text discarded' is slightly confusing, but the overall structure 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?

There is no output schema and no explanation of the returned 'connection methods,' error conditions, or how the optional inputs influence the lookup. Given the tool's apparent meta-purpose, the context is incomplete for reliable 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?

All nine parameters have descriptions, but most descriptions undermine their usefulness by saying the value is 'discarded' or only used for a 'shape check.' This clarifies that inputs may not affect the result, but it leaves an agent uncertain about what, if anything, should be passed to 'find a gateway.'

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

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

The description states a specific action (find), a resource (a public pay-per-call tool gateway), and an expected output (connection methods), with example task types. However, the relationship between the many optional parameters and the 'gateway' result is unclear, so it is not fully crisp.

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?

It offers only a broad 'such as weather, search, scrape, or voice' usage hint and does not explain when to choose this tool over the many sibling tools such as weather-hint, web-fetch, or normalize-url.

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

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

With no annotations provided, the description carries the full burden of disclosing behavior. It only says 'No browser is launched,' but does not explain whether network access occurs, how failures are reported, whether any side effects happen, or what the tool actually does to determine URL openness.

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 and contains no filler or redundant wording. It delivers the core action and an important constraint in just two short sentences.

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 definition lacks essential context for correct invocation given its complexity: no output schema, no explanation of return values, no indication which of the nine optional parameters are relevant, and no guidance on how the parameters relate to the stated URL-checking purpose.

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 parameter descriptions are incoherent relative to the tool's stated purpose. The url parameter is described as 'HTTPS URL to normalize or cite' rather than something to check, and most other parameters (city, zone, query, ref) are unrelated to checking whether a URL can be opened.

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 action and resource: check whether a URL can be opened, and adds the constraint that no browser is launched. However, the purpose is undermined by the input schema, which contains nine unrelated optional parameters (city, zone, query, etc.) that do not align with checking a URL.

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

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

The description gives almost no guidance on when to use this tool instead of alternatives. Sibling tools like fetch-status, normalize-url, and playwright-url-ok likely overlap, but no distinctions or explicit use conditions are provided beyond the single note that no browser is launched.

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 only says 'Expression discarded', which is ambiguous and does not clarify whether results are returned, side effects, or error behavior.

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

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

The description is very brief and front-loaded, but the second sentence 'Expression discarded' adds confusion rather than clarity. It is concise but not effectively structured.

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

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

The description lacks essential context: no explanation of how parameters relate to the calculation, no output schema, no return value description, and no usage context. The schema mismatch makes the tool's actual behavior nearly impossible to infer.

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 parameters (ref, url, city, feed, host, json, path, zone, query) are completely unrelated to arithmetic evaluation, and their descriptions ('discarded after the shape check', etc.) do not add meaningful semantics for a calc-eval tool.

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

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

The description states it evaluates 'a+b style arithmetic', which identifies a basic purpose, but no parameter in the schema corresponds to an expression or operands. The intended function is therefore unclear and inconsistent with the provided parameter set.

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

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

No guidance is given for when to use this tool versus any sibling tool. It does not mention alternatives, prerequisites, or typical 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?

No annotations are present, and the description only notes that identifiers are not retained. It does not disclose whether the tool performs reads/writes, whether it has side effects, or how data is handled beyond retention.

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 free of fluff, but its brevity contributes to vagueness rather than clarity. Structure is acceptable.

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

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

The tool has 9 optional parameters, no output schema, and no explanation of what a 'classification' result looks like or how inputs are combined. The description is incomplete for an agent to predict behavior.

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

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

All 9 parameters have schema descriptions, providing some individual meaning (e.g., 'IANA timezone name', 'JSON text to validate'), but the descriptions are eclectic and do not clarify how the parameters relate to the stated purpose of classification or compatibility.

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

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

Description states 'Show how this request is classified' but does not specify what classification means or what resource/action is involved. It does not distinguish from sibling tools 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?

No guidance is provided about when to use this tool versus any alternative. The description does not mention contexts, prerequisites, or exclusions.

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

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

No annotations are provided, and the description does not disclose any behavioral details such as side effects, permissions, or whether the operation is read-only. The phrase 'without WHOIS or data' is too vague to serve as a transparency statement.

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 but poorly structured. The phrase 'without WHOIS or data' is confusing and detracts from the otherwise simple statement. It could be clearer if the irrelevant clause were removed or rephrased.

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

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

With no output schema, no mention of return values, and a set of seemingly unrelated parameters, the tool lacks the contextual information needed to understand its intended behavior or how to invoke it correctly. The description does not fill these gaps.

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% coverage, the descriptions are largely irrelevant to the stated purpose. Parameters like 'city', 'zone', and 'query' have no obvious connection to splitting a hostname, while 'host' or 'url' are the only plausible inputs. The descriptions do not clarify how the tool uses them or which are required for the core action.

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

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

The description states the primary verb and object ('Split a hostname into labels'), but the trailing phrase 'without WHOIS or data' is ambiguous and does not clarify the tool's scope. It does not distinguish this tool from siblings that also deal with URLs or hostnames, such as normalize-url or figma-url-shape.

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 instead of alternatives. There is no mention of conditions, prerequisites, or typical use cases, leaving the agent without any decision support.

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 to lean on, and the description discloses only that it uses HEAD and returns status; it does not mention redirects, timeouts, error behavior, or that the many other schema parameters appear to be ignored.

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

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

The description is very concise and front-loaded, but it is almost too terse; the large, irrelevant parameter list in the schema undermines the structural 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?

The tool has nine optional parameters and no output schema, but the description does not specify the output format (e.g., numeric status code), which parameter is actually used, or why the other parameters exist; this leaves critical context missing.

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

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

Although every parameter has a description, those descriptions are largely unrelated to the tool's stated purpose—e.g., 'url' is described as 'HTTPS URL to normalize or cite', and params like 'ref', 'city', 'feed', 'json', 'zone', and 'query' are described as discarded or tied to other tools, actively misleading an agent about their role.

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 (HEAD), a specific resource (a public URL), and a precise output (status only), which clearly distinguishes it from sibling tools like normalize-url or web-fetch.

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

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

No guidance is given about when to choose this tool over alternatives, nor any conditions or caveats for use; the description simply states what it does without usage context.

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

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

The only behavioral note is that the path is discarded, but there is no mention of side effects, network access, or error behavior. With no annotations, this is insufficient for full 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 extremely concise with a clear structure. It does not waste words, though it might benefit from a bit more explanatory detail.

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

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

The tool lacks an output schema and annotations, and the description does not explain what result is produced or how the parameters relate to the input URL. This makes it incomplete for a caller to use effectively.

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

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

Although every parameter has a schema description, they are generic placeholders (e.g., 'City name for a public weather hint') that do not relate to parsing a Figma URL. The descriptions add no meaningful semantic value and are misleading.

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

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

The description clearly states a specific action ('Parse') on a specific resource ('Figma file URL'), distinguishing it from sibling URL tools. However, it lacks detail about what the parsed output contains.

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

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

No guidance is provided on when to use this tool versus alternatives like normalize-url or domain-shape. The description gives no context for appropriate use cases.

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

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

With no annotations, the description carries the full burden. It only says 'No disk access' and gives no detail about what 'looks safe' means, what the return value is, or whether it performs any validation beyond syntactic checks.

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 and front-loaded, with the core action stated first and the key side-effect constraint ('No disk access') immediately after. It avoids unnecessary wording, though it could benefit from a little more 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 that there are 9 parameters and no output schema, the description is too thin to provide complete context. It does not specify which parameter is the primary input, what the return shape looks like, or what criteria constitute a 'safe' path, leaving significant gaps for an agent.

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

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

Although every parameter has a description (100% coverage), most of them are irrelevant to the stated purpose (e.g., ref, url, city, feed, host, json, zone, query). Only 'path' directly matches the tool description, but the presence of many unrelated parameters creates confusion about which parameter should be used.

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

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

The description clearly states the operation ('Check whether a path looks safe') and explicitly notes 'No disk access', which helps distinguish it as a static check. However, it doesn't specify what kind of path (file, URL, etc.) beyond the parameter context.

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

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

No guidance is provided about when to use this tool versus alternatives such as browser-url-ok or normalize-url. The description does not mention use cases, prerequisites, or when it should not be used.

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

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

With no annotations, the description carries the full burden of explaining behavior, but it does not disclose that most schema parameters appear unrelated or are described as 'discarded'. It also does not clarify what happens with multiple inputs, whether a place lookup is required, or what output format is returned beyond 'latitude and longitude'.

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

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

The description is a single, short sentence that is easy to parse and front-loads the key information. It earns a high score for conciseness, though it omits important usage details that would make it fully self-contained.

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 nine optional parameters, no output schema, and no annotations, the description is far too thin to be complete. It does not specify which parameter identifies the place, what the coordinate format is, or how errors or invalid inputs are handled.

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

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

Although every parameter has a schema description, those descriptions seem mismatched with the geo-hint purpose (e.g., Git refs, RSS feeds, JSON validation, file paths). The description does not clarify which parameter is actually used for the place lookup, and all parameters are optional, leaving the agent uncertain about what to provide.

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 that the tool returns latitude and longitude for a place via Open-Meteo, which identifies the core purpose and distinguishes it from most sibling tools. It lacks an explicit verb like 'get' or 'return', but the meaning is still unambiguous.

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

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

The description provides no guidance on when to use this tool instead of the many similar sibling tools, nor does it explain which input parameter should be supplied to identify the place. There is no mention of alternatives, prerequisites, or 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 of behavioral disclosure. The single word 'Parse' gives no information about side effects, error handling, validation strictness, or what happens with malformed URLs. The description is nearly silent on behavior beyond the basic action.

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), which is concise but severely under-specified for a tool with nine parameters and no output schema. Important context such as required inputs, return value, and interaction with the 'shape check' pattern is omitted. This is under-specification, not effective conciseness.

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

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

For a tool with nine parameters, no output schema, and no annotations, the description is grossly incomplete. It does not explain what the tool returns, which parameters are mandatory, whether it performs validation or normalization, or how it relates to the sibling shape tools. An agent cannot reliably invoke this tool correctly based on the provided information.

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

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

Schema description coverage is 100%, so the schema documents each parameter, but the description adds no additional meaning and is misleading: it mentions only a GitHub URL while the schema includes nine parameters, many of which (city, feed, json, zone, etc.) are clearly unrelated to GitHub URL parsing. The description does not clarify which parameters are actually used or how they relate to the core purpose, so it fails to compensate for the schema's generic descriptions.

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

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

States a specific action (parse owner and repo) on a specific resource (GitHub URL), which distinguishes it from sibling shape tools like domain-shape or figma-url-shape. However, it does not specify the output format or the exact set of relevant inputs, leaving some ambiguity about what 'parse' produces.

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

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

No guidance on when to use this tool versus the many sibling shape/check tools (e.g., domain-shape, figma-url-shape). The description implies it is for GitHub URLs but does not state exclusion criteria or when to prefer an alternative. An agent must infer the applicability.

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

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

No annotations are provided, and the description does not disclose whether the tool is read-only, makes network calls, has rate limits, or returns partial data. The phrase 'Titles discarded' hints at output filtering but is vague.

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 main purpose. However, 'Titles discarded' is ambiguous and the description omits crucial parameter guidance, so conciseness comes at the expense 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?

With no output schema and a schema full of unrelated optional parameters, the description is not complete enough for an agent to invoke the tool confidently. It does not explain return format, errors, or how parameters relate to the tool's purpose.

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 exposes nine optional parameters (ref, url, city, feed, host, json, path, zone, query) with descriptions that have no connection to counting HN stories. The description adds no clarification about how, if at all, these parameters should be used.

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

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

The description states a clear action and target: count current Hacker News front-page stories. However, the input schema is entirely unrelated—no parameter refers to Hacker News—so the clarity is undermined by the mismatch.

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

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

The description gives no guidance on when to prefer this tool over the many siblings such as fetch-status, web-fetch, or normalize-url. It does not explain what makes hn-front-count the right choice for a given task.

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 disclosing behavior. It hints at the output content (common IANA timezone names) but does not state what the tool returns, whether it validates input, or how it handles the various parameters. This is a meaningful gap.

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

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

The description is extremely short and front-loaded, but it is a fragment rather than a complete sentence and omits essential behavioral information. It is under-specified rather than efficiently concise.

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

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

With 9 optional parameters, no output schema, and no annotations, a one-phrase description is far from sufficient. It does not explain which parameters matter, what the output looks like, or how this tool relates to the many sibling tools.

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

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

Schema description coverage is 100%, so the baseline is 3. The tool description adds no parameter-level meaning, but the schema already describes each parameter in detail, even though those descriptions seem disconnected from the stated purpose of listing IANA timezone names.

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

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

The description identifies the subject (common IANA timezone names) and the intended context (clock calls), but it is a noun phrase without an explicit verb like 'lists' or 'returns.' It does not distinguish this tool from sibling clock-related tools such as timezone or utc-time.

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

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

The phrase 'for clock calls' implies when the tool might be useful, giving a general usage context. However, it offers no explicit guidance about when not to use it, nor does it name alternatives among the many 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?

There are no annotations, so the description carries the full burden. It mentions 'group counts only' but does not disclose network behavior, error handling, rate limits, or any side effects.

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

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

The description is a single, concise sentence with no unnecessary words, and the schema is clearly structured.

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

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

The description is too sparse given the complexity of 9 optional, mostly unrelated parameters and no output schema. It does not explain which parameters are relevant, what input is expected, or the exact format of the returned group counts.

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 descriptions cover 100% of parameters, the descriptions are irrelevant or misleading for a robots.txt tool (e.g., 'Git ref name', 'City name for a public weather hint'), and none clearly map to the fetch 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 clearly states the action ('Fetch'), the target resource ('a public robots.txt'), and the output ('return group counts only'), which distinguishes it from generic fetch 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 alternatives such as web-fetch or fetch-status, nor any conditions for choosing it.

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

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

The phrase 'Key discarded' suggests the input is not retained, but there is no mention of other behavioral traits such as validation rules, error handling, or side effects. Without annotations, the description carries the burden and fails to provide meaningful 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 very concise at only two sentences, with no fluff. However, the structure is minimal and could benefit from a clearer separation of purpose and behavior.

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

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

Given the tool has 9 optional parameters and no output schema, the description is severely incomplete. It omits essential details about which parameter to provide, what constitutes a valid Jira key shape, and what the tool returns or implies.

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

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

The description does not explain how any of the nine parameters relate to the Jira key shape check. The schema descriptions are generic and unrelated (e.g., 'City name for a public weather hint'), and the description itself adds no clarification, leaving parameter usage entirely ambiguous.

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

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

The description states a specific action and resource: 'Check a Jira issue key shape.' This clearly identifies the tool's purpose. However, it does not specify which parameter contains the Jira key or what shape criteria are applied, slightly reducing clarity.

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 explain when to use this tool over siblings like 'domain-shape' or 'github-repo-shape', nor does it indicate the appropriate input format or context.

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

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

The description does disclose one behavioral trait: 'Body discarded' implies that only the HTTP status is returned and the response body is not provided. However, with no annotations, it does not mention error behavior, rate limits, authentication, or whether extra parameters are ignored, so transparency is only partial.

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

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

The description is extremely concise and has no filler words. However, it is too terse to compensate for the complex schema, and it lacks any structured breakdown of behavior or usage, so conciseness comes at the cost of completeness.

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

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

Given the tool has nine optional parameters and no output schema, the description is severely incomplete. It does not explain what happens when multiple parameters are provided, which parameter is the primary input, what the return value looks like, or what errors can occur. The one-sentence description is inadequate 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%, which would normally give a baseline of 3, but the parameter descriptions are confusing and often contradict the tool's stated purpose. For example, 'url' is described as 'HTTPS URL to normalize or cite' rather than the URL whose status is fetched, and many parameters are described as 'discarded' without explaining that the tool only needs one primary input. The description adds no clarity about which parameters are relevant or how they map to the 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 states a verb and resource: 'HTTP status for a public library docs URL.' However, the input schema contains nine unrelated parameters (ref, city, feed, json, zone, query, etc.) with descriptions like 'discarded after the shape check,' which makes it very unclear which parameter is actually used or what the tool really does. The name 'lib-docs-hint' and the schema do not align with the description, weakening purpose clarity.

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 instead of sibling tools such as fetch-status, web-fetch, browser-url-ok, or normalize-url. No conditions, alternatives, or exclusions are mentioned, leaving the agent to guess when this 'hint' 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 burden of explaining side effects, read-only behavior, and output. It only says values are discarded, which gives minimal insight into whether the operation is purely computational or has any external 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 very short and front-loaded, but it is too terse to convey the necessary input mapping or usage context. It has no extraneous words, but 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?

Given 9 parameters and no output schema, the description is not contextually complete. It does not explain what the function returns, how to specify the JSON input, or why so many unrelated parameters exist. A user would not be able to confidently invoke this tool 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?

The schema descriptions are largely unrelated to the tool purpose. For example, json is described as 'JSON text to validate; discarded after the check' rather than 'the object whose keys will be counted', and many parameters like ref, url, city, and zone have no apparent connection to counting keys. The description does not clarify which parameter is the actual JSON object.

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

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

The description clearly states the core action: count keys in a JSON object and ignore values. This distinguishes it from sibling tools like validate-json, though it does not name the input parameter that holds the 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?

No explicit guidance is given about when to use this tool versus alternatives such as validate-json or search-query-len. The description only states what it does, not when it should be preferred or when it should not be used.

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

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

The description explicitly notes that query and fragment are dropped, which is useful behavioral information. However, it does not disclose any other side effects, error conditions, or security implications, and the many unrelated parameters create confusion about actual behavior.

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

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

The description is extremely concise, consisting of two short sentences that convey the core functionality without unnecessary detail. This is ideal for a tool description.

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

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

Given the tool's apparent simplicity, the description provides minimal context. It does not explain the purpose of the extra parameters, nor does it specify output structure or any preconditions. The mismatch between description and schema leaves the agent under-informed.

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

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

Although schema coverage is 100%, the parameter descriptions are generic and largely irrelevant to URL normalization (e.g., 'ref' as Git ref, 'city' as weather hint). The description adds no clarification, and the parameters actively mislead about the tool's actual inputs.

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 origin, host, and path from a URL, which is a specific and distinct operation among the sibling tools. However, the presence of many unrelated parameters in the schema slightly muddies the core 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. The description does not mention any conditions, alternatives, or exclusions, leaving the agent without decision support.

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 transparency burden. It reveals only that no browser is launched; it does not disclose that a network request may be made, whether it is read-only, or what success/failure 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 only two short sentences with no redundant phrasing. It is concise, though it sacrifices needed 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?

The tool gives no output schema, no return-value description, no error conditions, and no indication of which of the nine optional parameters are actually relevant. An agent cannot infer what arguments to provide or how to interpret the result.

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

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

Although every parameter has a description, most are unrelated to checking a URL (ref, city, feed, zone) and several are described as discarded. The main 'url' parameter is described as 'normalize or cite' rather than 'open', so the parameter descriptions actively mislead about how to call the tool.

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

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

The description names a clear action ('check whether') and resource ('a URL'), and 'No browser is launched' distinguishes it from browser-based alternatives. It is somewhat vague about what 'opened' means (HTTP status? reachability?), but the core purpose is identifiable.

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

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

No guidance is given for when to prefer this tool over siblings such as browser-url-ok, fetch-status, or normalize-url. 'No browser is launched' is a constraint, not a usage condition.

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 transparency burden, but it only discloses that the query is discarded. It does not specify the return value, error behavior, or the fate of the many other accepted parameters, some of which have non-discard descriptions, creating confusion.

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

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

The description is extremely short and front-loaded: two sentences, both informative. It could be slightly clearer about the parameter's disposal, but there is no redundancy or wasted text.

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

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

For a tool with nine optional parameters and no output schema, the description is too sparse. It omits the return format, does not explain the role of the unrelated parameters, and provides no guidance on selecting this tool over sibling tools. An agent would likely be unsure whether to supply any of the extra fields.

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

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

Although every schema parameter has a description, several are unrelated to counting a query and are described with behaviors that suggest they do something (e.g., url 'normalize or cite', zone 'IANA timezone name'). The query parameter is clear, but the tool description adds no clarification about whether the other parameters are ignored, making the parameter list misleading.

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

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

The description states a specific action and target: 'Count characters in a search query.' This clearly conveys the primary purpose. The phrase 'Query discarded' adds slight ambiguity about whether the query itself is discarded or only the parameter after use.

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

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

No when-to-use guidance is provided. The description does not mention alternatives, trade-offs, or conditions such as checking query length for API limits, nor does it reference 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?

No annotations are provided, so the description carries the full burden of explaining behavior. It does not disclose side effects, output shape, whether inputs are read-only, or what happens when multiple parameters are supplied.

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 and is concise in length, but it sacrifices necessary detail and structure. It does not front-load the actual operation or parameter usage.

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

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

With nine optional parameters and no output schema, the tool needs substantial contextual explanation. The description is far too incomplete to tell an agent what input to supply, what output to expect, or how to handle the conflicting parameter hints.

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 descriptions give individual parameter hints, but the tool description does not explain how parameters like url, json, path, zone, or query relate to a catalog of HTTP status codes. This creates a semantic mismatch and leaves the agent unsure which parameter is relevant.

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

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

The description identifies the resource as a 'catalog of common HTTP status codes', but does not state what action the tool performs or how this relates to the tool's name. It is neither a tautology nor fully misleading, but it is too vague to distinguish effectively from sibling tools like fetch-status or wiki-title-ok.

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

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

There is no guidance about when to use this tool versus alternatives such as fetch-status, normalize-url, or validate-json. The description provides no context, prerequisites, or examples of appropriate invocation.

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 states only a unit conversion, but the input schema includes unrelated parameters (url, city, feed, etc.) with no explanation of how they relate. This is misleading: an agent expecting a simple conversion would not anticipate these parameters, and no behavior is disclosed about what happens to them.

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

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

The description is extremely short, but this is under-specification rather than conciseness. For a tool with 9 parameters, a one-line phrase is insufficient to convey necessary context. It is not front-loaded with useful information; it simply repeats the name.

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

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

Given the high complexity (9 parameters, no required fields) and absence of annotations or output schema, the description is completely inadequate. It does not explain the return format, the role of each parameter, or any side effects. An agent has no way to correctly invoke this tool based on the current description.

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

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

Although schema description coverage is 100%, the description adds zero meaning beyond the schema. The parameters are individually described (e.g., 'Git ref name; discarded after the shape check') but the tool's stated purpose ('Stone to pounds') has no connection to these parameters. The agent cannot infer how to use any parameter to achieve the conversion, so the description fails to compensate for the schema's irrelevance.

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 'Stone to pounds' is essentially a restatement of the tool name 'st-to-lb' with no verb or resource specification. It does not clarify what the tool does beyond the implied unit conversion, and it fails to differentiate from the many sibling tools (e.g., calc-eval, normalize-url). For an agent, this is tautological and unhelpful.

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

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

There is no guidance on when to use this tool versus alternatives. No mention of use cases, conditions, or exclusions. The description is a single phrase with no context, leaving the agent to guess whether to select it for any given task.

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

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

With no annotations, the description carries the full burden. It does not mention side effects, read-only nature, security implications, or error behavior. The phrase 'Prompt discarded' is ambiguous and could imply that all inputs are ignored, but this is not clearly stated, and it conflicts with the existence of parameters.

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

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

The description is very short (one sentence) and lacks necessary detail. Given the tool has 9 parameters and no output schema, this brevity is insufficient and undermines clarity. The structure is overly minimal for the tool's apparent complexity.

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

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

The description does not specify the output format or structure of the 'three-step thinking template,' nor does it explain how inputs affect the output. It fails to provide enough context for an agent to correctly invoke the tool or interpret its result, especially without an output 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?

The parameter descriptions are generic and unrelated to the tool's stated purpose. For example, 'url' is described as 'HTTPS URL to normalize or cite' and 'city' as 'City name for a public weather hint,' which have no obvious connection to returning a thinking template. The schema descriptions do not help clarify how each parameter influences the output.

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

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

The description 'Return a three-step thinking template' states a verb and an object but is extremely vague. It does not clarify what a 'thinking template' is or how it relates to the provided parameters, making the tool's actual purpose ambiguous.

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

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

No guidance is provided on when to use this tool versus any of the many sibling tools (e.g., browser-url-ok, calc-eval, etc.). There is no context about typical scenarios, constraints, or alternatives, leaving an agent without direction.

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 only states the core function and gives no information about error handling, timezone validity, return format, or how the other eight parameters are ignored. This is a 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, front-loaded sentence with no wasted words. It is appropriately concise for the core purpose, though given the tool's 9-parameter schema, a slightly more detailed note about which parameters matter would improve clarity without bloating the text.

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

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

The description is incomplete for the tool's complexity. It has 9 parameters, most of which seem irrelevant to the stated purpose, and no output schema. The description does not explain that only 'zone' is used, how errors are reported, or what the return value looks like, leaving significant gaps for an agent.

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 already has a descriptive schema entry. The description adds no extra meaning beyond identifying 'zone' as the timezone name, which is already obvious from the schema. It does not clarify why the other parameters exist, but it does not contradict them.

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

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

The description states a specific action ('Current time') and a clear resource ('named IANA timezone'), which is unambiguous. However, it does not distinguish itself from the sibling tool 'utc-time', which may overlap in purpose, so it lacks explicit differentiation.

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

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

No guidance is given on when to use this tool versus alternatives like 'utc-time' or 'iana-zones'. The description does not state any preconditions, exclusions, or typical use cases, leaving the agent to infer appropriateness.

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

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

With no annotations, the description must disclose behavior. It only states the output (timestamp) but does not mention side effects, error conditions, or that all parameters are discarded after shape checks. The description is grossly insufficient for a tool with this complexity.

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, but conciseness is not the same as under-specification. It is a single sentence with no structure or prioritization. It is short but lacks necessary content to guide the agent.

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 completely inadequate. An agent cannot determine what inputs are relevant, what the output format is, or how to use it correctly.

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

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

Schema coverage is 100%, but the description adds no value about how parameters relate to the tool's purpose. The schema describes each parameter, but the tool description gives no hint why a UTC time tool accepts a city or a URL. The agent cannot understand the intended usage from the description.

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

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

The description 'Current UTC timestamp.' clearly states the tool returns the current UTC time. It identifies the resource (UTC timestamp) and implies the action (get). However, it does not differentiate from sibling tools like 'timezone' or 'iana-zones', so it loses a 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?

There is no guidance on when to use this tool versus alternatives. The description is a single sentence with no context about preferred use cases or when a sibling tool would be more 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 must carry the full burden. It discloses that the 'body' is discarded, but this is vague (does it refer to the request body or the 'json' parameter?) and no other behaviors (return format, side effects, required inputs) are disclosed. The repeated 'discarded' phrasing adds little beyond the schema's own 'discarded after the check' notes.

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

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

The description is extremely concise (one sentence) and front-loaded with the purpose, but it omits essential context. It is under-specified rather than efficiently structured – the single sentence does not earn its place because it fails to address the tool's actual breadth.

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 woefully inadequate. It does not explain what the tool returns, how to invoke it correctly, which parameters are relevant, or any side effects. An agent would have no way to use this tool correctly beyond guessing.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning to the parameters – it doesn't explain how 'ref', 'url', 'city', etc. relate to JSON validation. Since the schema already documents each parameter, the description contributes no extra semantic 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 body is valid JSON.' This is specific and distinguishes the core function from siblings by name. However, it ignores the 8 other parameters in the schema, so the stated purpose is incomplete and could mislead an agent into thinking only the 'json' parameter matters.

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

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

There is no guidance on when to use this tool versus its 26 siblings. No context, no exclusions, no alternatives are mentioned. The one-sentence description provides zero usage direction.

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 bears the full burden of behavioral disclosure. The one-line description reveals only that it fetches temperature via Open-Meteo, but says nothing about how inputs are handled, whether network calls are made, what happens with the nine schema parameters, or any side effects. The schema hints at discarding inputs, but the description itself provides minimal behavioral context.

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

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

The description is a single, front-loaded sentence with no filler. It is efficient and to the point. However, given the tool's complexity (9 parameters, none required), the brevity borders on under-specification, though it is still concise rather than verbose.

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, many seemingly unrelated to weather (ref, url, feed, host, json, path, zone, query), and no output schema or annotations. The description covers only the city parameter and the weather purpose, offering no explanation for the other inputs or the return format. This is severely incomplete for an agent to call correctly.

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

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

Schema description coverage is 100%, so the schema already documents every parameter. The description adds only the context that the tool is about weather, which is not evident from parameter names alone. It does not elaborate on how parameters like ref, url, or feed relate to the weather function, leaving ambiguity. This meets the baseline but adds little 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 states a specific action: getting the current temperature for a city via Open-Meteo. It names the resource (city) and the provider, and the tool name 'weather-hint' reinforces this. However, it does not explicitly differentiate from sibling tools like geo-hint or lib-docs-hint, though the weather focus is implicit.

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

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

No guidance is given on when to use this tool versus the 27 siblings. The description only states what it does, not when it is the appropriate choice or what conditions select it. There is no mention of alternatives or exclusions, leaving the agent to guess.

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 that the body is discarded, which is useful, but it omits that the tool also performs shape checks for city, JSON, timezone, etc., as implied by the schema. The description is misleading because it only covers URL status/content type while the schema suggests multiple distinct behaviors.

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

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

The description is a single sentence, which is concise and front-loaded with the main purpose. However, given the complexity of the schema (9 parameters, multiple potential uses), the description is under-specified, and the brevity does not compensate for the lack of important behavioral 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?

For a tool with nine parameters, no output schema, and no annotations, the description is severely incomplete. It only explains the URL status/content type aspect and ignores the other parameter uses. An agent would not understand the full scope of the tool or how to correctly invoke it for 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 coverage is 100% with each parameter having a description, so the baseline is 3. The tool description adds no additional parameter information beyond what the schema provides, and it does not clarify the relationships or priorities among the nine 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 states a specific action ('HTTP status and content type') and a specific resource ('public URL'), which is clear. However, it does not differentiate from sibling tools like fetch-status or browser-url-ok, and the schema includes parameters for many other purposes (city, json, zone) that the description does not mention, so it is not fully aligned with 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?

The description gives a minimal context ('public URL') but provides no guidance on when to use this tool versus alternatives like normalize-url or fetch-status. It does not mention exclusions, prerequisites, or any conditions that would select this tool over its many siblings.

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

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

No annotations are present, and the description only says 'Title discarded after the call' even though no title parameter exists. It fails to disclose what the tool actually does with inputs, what it returns, or any side effects.

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

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

The description is only one sentence and is concise, but the phrase 'Title discarded after the call' introduces confusion rather than clarity. It does not front-load useful information about the actual operation.

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

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

With no output schema, no required parameters, and a schema that does not match the description, the definition is incomplete. An agent cannot infer expected inputs, outputs, or behavior from the provided information.

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

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

Although the schema has 100% description coverage, the parameter descriptions are generic and unrelated to checking a Wikipedia title. They do not clarify how any parameter relates to the tool's stated purpose, so the semantics are misleading.

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

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

The description states the tool checks whether a Wikipedia title exists, but the input schema contains no 'title' parameter and instead lists unrelated parameters like 'ref', 'url', and 'city'. This makes the actual purpose confusing and not actionable as described.

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 sibling tool. The description provides no usage context, and the mismatch between the described purpose and the actual schema leaves an agent without clear direction.

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