Pascals to bar

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 does mention 'Task text discarded' and 'no disk access' for a parameter, but it doesn't disclose network usage (implied by 'remote MCP hops'), side effects, or what happens to other inputs. It's not misleading but far from transparent about the tool's behavior.

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

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

The description is brief (two sentences) and front-loaded with the main action, but it's so terse that it omits critical information. Conciseness is not a problem; clarity is. The structure is acceptable but the content is insufficient.

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 severely incomplete. It doesn't explain how inputs are used, what the output format is, or how to interpret the returned artifacts. An agent would struggle to call this tool correctly without additional context.

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

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

Schema coverage is 100% (every parameter has a description), so the baseline is 3. The tool description adds no additional meaning beyond what the schema already provides; it doesn't explain how parameters like 'url', 'city', or 'json' relate to the gateway discovery 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 says 'Find a public pay-per-call tool gateway (Monid)' and lists outputs (CLI setup, how-it-works, skill file, remote MCP hops), but it doesn't clarify what the tool actually does with its 9 heterogeneous inputs. It doesn't differentiate from siblings like browser-url-ok or validate-json; the purpose is vague and the connection between inputs and outputs is missing.

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 mentions it's for finding a gateway, but doesn't specify what input triggers it or when an agent should prefer it over other shape-checking or validation tools. No exclusions or prerequisites 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions 'Expression discarded' but provides no detail on side effects, required permissions, error handling, or return values. The description does not contradict annotations (none exist), but it offers no behavioral transparency at all.

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 it is under-specified rather than concise. It fails to convey the tool's function or usage for a 9-parameter tool. There is no front-loading of critical information; the only sentence is vague and misleading.

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

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

Given the complexity (9 parameters, no output schema, no annotations), the description is grossly incomplete. It does not explain how the parameters are used, what the tool returns, or any constraints. An agent has no basis to invoke this tool correctly.

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

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

Despite 100% schema coverage, the description adds no meaning to any parameter. It does not connect the 9 parameters to the tool's purpose, and the arithmetic claim is irrelevant. The description neither reinforces nor clarifies parameter usage, so it provides zero 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 claims the tool 'Evaluate a+b style arithmetic', but the schema contains no arithmetic-related parameter (no expression, no operands). The actual parameters (ref, url, city, etc.) are unrelated to arithmetic, so the stated purpose is misleading. It fails to describe what the tool actually does with these 9 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 given on when to use this tool versus its siblings. The description is a single vague sentence with no context, alternatives, or conditions. An agent cannot determine when calc-eval would be appropriate over tools 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.

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 'No identifiers are retained' which is a privacy note, and several parameter descriptions mention 'discarded after the check,' implying a non-persistent, read-only operation. However, it doesn't explicitly state whether the tool makes network calls, accesses local resources, or has side effects, and it doesn't describe the output format. Partial disclosure only.

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 sentence, which is concise, but it's under-specified rather than efficient. It omits critical information about the tool's purpose and output, so the brevity is not an asset. There is no structural organization or front-loading of key details beyond a vague statement.

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

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

This tool has 9 optional parameters spanning many domains (Git refs, URLs, cities, RSS, JSON, paths, timezones, queries), yet the description gives no indication of what classification means, what output to expect, or how the tool integrates with the sibling tools. With no output schema and no annotations, the description is severely incomplete for an agent to call this tool 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?

Schema description coverage is 100%, so the baseline is 3. The tool description adds no parameter-specific detail, but the schema itself provides rich descriptions for all 9 parameters (e.g., 'discarded after the shape check'). The description doesn't need to add more since the schema covers it, so the baseline holds.

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

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

The description says 'Show how this request is classified' which is a verb+resource but extremely vague. It doesn't clarify what 'classified' means, what compatibility refers to, or what distinguishes this from the many sibling tools that check specific inputs. It's not a tautology but gives little actionable meaning.

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 its 29 siblings. The description provides no context about what kind of request classification it performs or what inputs would make it the right choice. An agent has no basis to select it over alternatives.

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 disclose behavior fully. It claims to split hostnames, yet the schema accepts 9 unrelated parameters (ref, city, feed, json, path, zone, query) with descriptions indicating they are 'discarded' or checked. The description does not acknowledge these other functions or clarify how the tool behaves for non-hostname inputs, making the tool's actual behavior opaque and potentially misleading.

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

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

The description is a single, tight sentence with no wasted words. It front-loads the primary action and includes a useful qualifier. However, it is so short that it sacrifices necessary detail, which is a minor structural drawback.

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

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

The tool has 9 optional parameters, no output schema, and no annotations. The description only explains one narrow function (hostname splitting) and omits any guidance on the other 8 parameters, error handling, return format, or use cases. This is severely incomplete for a tool of this 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?

Schema coverage is 100% – every parameter has a description in the schema, so the baseline is 3. The tool description adds no parameter-specific meaning beyond the schema, and does not clarify how the hostname parameter relates to the others. No extra semantic value is provided.

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 ('split a hostname into labels') and adds a differentiating caveat ('without WHOIS or ownership data'), which helps distinguish it from ownership-oriented tools. It does not explicitly reference sibling shape tools like github-repo-shape or jira-key-shape, but the core purpose is unambiguous.

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

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

The only guidance is the negative clause 'without WHOIS or ownership data', implying an alternative for WHOIS but never naming one. There is no statement of when to use this tool versus other shape checkers, nor any mention of prerequisites or expected input types beyond the schema. An agent gets little direction on selection.

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

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

No annotations are provided, so the description carries full behavioral burden. It claims to only HEAD a public URL, but the schema indicates it accepts many other parameter types with 'discarded' notes, implying a broader multi-purpose shape-check behavior. This is misleading and contradicts the stated scope. It also does not disclose any side effects, rate limits, or what 'status' means in the response.

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 brief (one sentence), which is concise, but it is so sparse that it lacks essential context. It front-loads the verb and resource, but the structure does not accommodate the tool's apparent multi-parameter nature. It is under-specified rather than appropriately concise.

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

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

For a tool with 9 optional parameters and no output schema, the description is severely incomplete. It does not explain how each parameter maps to behavior, what 'status' means, what the return value looks like, or any constraints. An agent would have to infer everything from parameter descriptions, which is inadequate for a tool that appears to support multiple distinct checks.

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

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

Schema description coverage is 100%, with each parameter individually described (e.g., 'Git ref name; discarded after the shape check'). The tool description adds no additional meaning beyond the schema, so the baseline of 3 applies. It does not clarify how parameters interact or which are required for a URL status check.

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 the result (status only), but the parameter list accepts nine diverse fields (ref, city, feed, json, zone, query, etc.) that are unrelated to a simple URL HEAD. This creates ambiguity about what the tool actually does and does not distinguish it from siblings like web-fetch or browser-url-ok, which are also URL-related.

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. It does not mention any sibling tools, conditions for use, or exclusions. The description is a single sentence with no context on selection.

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

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

With no annotations, the description carries the full behavioral burden, but it only discloses that the path is discarded. It does not state whether the tool returns a boolean, parsed components, or an error, and it does not address the many schema fields that appear unrelated to a Figma URL.

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. Both statements carry meaning, and the primary action is front-loaded before the behavioral caveat.

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 required fields, no output schema, and no annotations, yet the description is only seven words. It fails to explain return values, which parameter to supply, or what the unrelated schema fields (city, feed, json, path, zone, etc.) are doing in this 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 coverage is 100%, so the baseline is 3 even without parameter details in the description. The description does add that the URL should be a Figma file URL, but it does not clarify the role of the other eight parameters, which is a notable 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 names a specific verb and resource: 'Parse a Figma file URL,' which is enough to distinguish it from generic URL tools like normalize-url and browser-url-ok. The added note 'Path discarded' clarifies a key behavior, though the schema's unrelated parameters make the exact scope slightly blurry.

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 siblings such as normalize-url, domain-shape, or file-path-ok. The description does not state any exclusions, prerequisites, or alternative conditions, leaving the agent to infer usage solely from the tool 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 carries the full burden of behavioral disclosure. It only states 'No disk access,' which is a safety guarantee but does not describe return values, whether the operation is read-only, what happens on an unsafe path, or any side effects. The description is minimal and leaves critical behavioral details 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 sentence, making it highly concise and front-loaded with the core purpose. However, it is almost too sparse; while conciseness is good, it sacrifices necessary detail. It earns a 4 for efficiency but not a 5 because it omits key context.

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

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

For a tool with 9 optional parameters, no required fields, and no output schema, the description is inadequate. It does not clarify which parameters are relevant or ignored, what the expected input is, or what the result indicates. The agent cannot determine how to invoke it correctly or interpret the outcome without additional 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?

The schema provides detailed descriptions for all 9 parameters, including notes on when they are discarded. The tool description adds no additional meaning beyond what the schema already covers, but it does not contradict it either. Since schema coverage is 100%, the baseline is 3; the description does not 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 states a clear verb ('check') and resource ('path'), and notes the safety aspect ('looks safe'). However, it is vague about what constitutes 'safe' and does not differentiate this tool from siblings like 'browser-url-ok' or 'domain-shape' that also perform shape/safety checks. It is not a tautology, but it lacks the specificity needed to distinguish it without relying on the schema.

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. It does not mention that it is for file paths specifically, nor does it exclude URLs, hostnames, or other entities. There is no explicit or implicit direction for selecting 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?

No annotations are provided, so the description carries the full burden. It only states the core function and does not disclose what happens to inputs (some are described as 'discarded' in the schema but not in the tool description) or any side effects or output format.

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 and front-loads the primary function. However, its brevity omits necessary context about the parameter set, so it earns a high but not perfect 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?

With 9 optional parameters and no output schema, the description is inadequate to guide correct invocation. It does not explain the role of each parameter, how they relate to the geolocation function, or what the tool returns. An agent would struggle 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?

The schema already describes each parameter in detail (100% coverage), but the description adds no meaningful link between the stated geolocation purpose and the many unrelated parameters. It fails to clarify which parameter is the 'place' or how others are 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 names a specific function (latitude/longitude via Open-Meteo) but the input schema contains 9 unrelated parameters (ref, url, feed, host, json, path, zone, query), making the tool's actual scope ambiguous. It distinguishes the core purpose but not the full range of behaviors.

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 sibling tools like weather-hint or timezone, nor which of the 9 parameters is appropriate for a given call. The agent is left to infer usage from the schema alone.

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

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

No annotations are present, so the description must disclose behavioral traits. It only says 'Titles discarded,' which is cryptic and does not explain the output format, network dependency, or the role of the nine parameters (many of which are described as 'discarded'). The tool's actual behavior remains largely opaque.

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

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

The description is two sentences with minimal waste. The first sentence clearly states the action; the second adds a note about titles. It is appropriately short, though the second sentence is vague and could be clarified. Overall, it earns a 4 for efficiency.

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 no annotations, the description must fully equip the agent. It fails to mention what the tool returns (likely a number), how the nine parameters are used (they appear irrelevant), and any edge cases. For a simple counting tool, the description is too thin to support correct invocation.

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

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

Schema description coverage is 100% with each parameter having a description. However, the tool description does not link these parameters to its purpose. The parameter descriptions are informative individually (e.g., 'Git ref name; discarded after the shape check') but do not explain why they exist for this tool. Since the schema already documents each parameter, the description adds no extra meaning, warranting the baseline score.

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

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

The description states a specific action ('Count current Hacker News front-page stories') with a clear resource (Hacker News front page). It distinguishes this tool from siblings like 'web-fetch' or 'fetch-status' by implying it returns a count rather than content. Even though it doesn't name an alternative, the verb and resource are 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?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention any conditions, prerequisites, or exclusions. Given the large sibling list, an agent has no help in deciding whether this tool is appropriate for a 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 side effects, permissions, or return behavior. The one-liner gives no such detail—it doesn't mention that the tool may discard inputs, avoid disk access, or perform checks. Behavioral transparency is essentially absent.

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 brief—a single sentence—but it is under-specified rather than concise. It front-loads no useful context and leaves the agent with no actionable information about the tool's behavior or scope. Under-specification is penalized, so a 2 is warranted.

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 and no output schema, the description must compensate by explaining what the tool does with these inputs. It fails entirely, giving only a vague mention of timezone names. The tool's actual operation remains opaque, making it impossible for an agent to call it correctly.

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

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

Schema description coverage is 100%, so each parameter is individually documented. The tool description adds no additional meaning beyond the schema; it doesn't clarify how the parameters relate to the stated timezone purpose. Per the rubric, baseline 3 is appropriate when the schema fully documents parameters, even though the description adds 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 'Common IANA timezone names for clock calls,' which suggests a resource for timezone lookups. However, the input schema contains nine unrelated parameters (url, json, path, query, etc.), indicating the tool likely performs a broader validation or normalization role. The description is vague and fails to distinguish this tool from siblings like timezone or utc-time.

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

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

There is no guidance on when to use this tool versus alternatives. The sibling list includes timezone, utc-time, weather-hint, and others, but the description offers no conditions or exclusions to help an agent choose correctly.

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

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

With no annotations provided, the description must fully disclose behavioral traits. It mentions that it returns only group counts, which is useful, but it does not disclose side effects (e.g., network access, discarding of parameters), error behavior, or that some schema parameters are explicitly marked as discarded after a shape check. The description's claim to 'fetch' conflicts with the schema's note that some parameters are 'discarded after the shape check,' indicating a lack of transparency about the actual operational 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, front-loaded sentence, which is concise. However, it is under-specified for a tool with nine parameters and no output schema, providing insufficient structure to guide an agent on how to invoke it correctly. It is not overly verbose, but it lacks the necessary detail to be considered well-structured.

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

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

Given the tool's complexity (9 parameters, no output schema, no annotations), the description is severely incomplete. It does not explain what 'group counts' refers to, how parameters map to the action, the return format, or error handling. An agent would be left guessing about the actual behavior and usage, making this far below the minimum viable description.

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

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

The input schema has 100% description coverage, so each parameter is self-documented. The tool description adds no additional meaning beyond the schema—it does not clarify which parameter is the robots.txt URL or how parameters relate to the action. Per the rubric, a baseline of 3 is appropriate when the schema does the heavy lifting, and the description does not exceed that.

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 ('Fetch'), a specific resource ('public robots.txt'), and a specific output ('return group counts only'), making the tool's core purpose clear. However, it does not differentiate from siblings like 'fetch-status' or 'domain-shape' beyond the robots.txt target, so it loses a point for not explicitly positioning itself against alternatives.

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

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

The description provides no guidance on when to use this tool versus the many siblings (e.g., 'fetch-status', 'web-fetch', 'domain-shape'). It does not mention any preconditions, alternative tools, or scenarios where this should be preferred, leaving the agent to guess based on the name alone.

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

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

With no annotations, the description carries the full burden. It mentions 'Body discarded' as a behavior, but it doesn't disclose that most parameters are ignored, nor does it clarify the tool's read-only nature or any side effects. The schema descriptions hint at discarding, but the description adds minimal value beyond that.

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

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

The description is a single short sentence, but it is under-specified rather than appropriately concise. It lacks essential usage and behavioral context, making it too terse to be useful. No important information is front-loaded beyond a bare purpose statement.

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

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

Given the tool has 9 optional parameters, no output schema, and many similar siblings, the description is severely incomplete. It doesn't explain the output format, how to choose parameters, or when to invoke this tool over alternatives. An agent would struggle 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%, so baseline is 3, but the description adds no parameter guidance. It doesn't indicate that the 'url' parameter is the primary input or explain the relevance of the other eight parameters, all marked as discarded. The mismatch between 'library docs' and the generic schema further confuses 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 states a specific verb ('HTTP status') and resource ('public library docs URL'), but it is vague and doesn't match the schema's generic 'url' parameter. It fails to differentiate from siblings like fetch-status or browser-url-ok, which also report 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 provided on when to use this tool versus alternatives. The description gives no conditions, prerequisites, or exclusions, leaving the agent to guess among many similar URL-checking siblings.

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

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It only mentions that values are discarded, but says nothing about error handling, invalid JSON behavior, side effects, or the nature of the count output. This is critically insufficient for a tool with 9 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 a single sentence, which is concise, but it is under-specified for a tool with 9 parameters and no output schema. Conciseness is not effective when essential details like input selection and output format are missing.

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 is moderately complex (9 parameters, no output schema, no annotations), yet the description provides almost no context: it doesn't state which parameter is the JSON, what the return value looks like, how errors are handled, or when it should be used. The description is grossly incomplete.

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

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

Schema description coverage is 100%, so the baseline is 3, but the tool description adds no clarification about which parameter to use for the JSON object. The 'json' parameter description says 'validate', which contradicts the counting intent, and the tool description does not resolve this ambiguity. Thus the description fails to add value beyond the schema.

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

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

The description states a clear action ('Count keys in a JSON object') but does not specify which of the 9 input parameters holds the JSON text, nor does it differentiate from sibling tools like validate-json that also handle JSON. The purpose is ambiguous despite a concrete verb.

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 scenarios, exclusions, or context where counting keys is preferred over validating or other operations.

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 does disclose that query and fragment are dropped, which is useful. However, it fails to clarify which of the nine parameters is the URL input, what happens to the other eight parameters, whether the host is lowercased, or how invalid URLs are handled. This is only partial 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 sentence, very concise and front-loaded with the core purpose. However, it is so brief that it omits critical details about input selection and behavior. While not verbose, it under-specifies, so it is not an ideal structure. A score of 3 reflects that it is concise but incomplete.

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 9 parameters, no annotations, and no output schema, this description is severely inadequate. The agent cannot determine which parameter to use, what the output format is, or what the other parameters are for. The description provides almost no context to support correct invocation, making it nearly useless.

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. However, the tool description does not add meaning beyond that—it says 'for a URL' but does not specify which parameter is the URL. The schema itself lists many discarded parameters, but the description does not direct the agent to the correct one, creating ambiguity. Baseline is 3 for high coverage, but the description fails to clarify the primary input, so a 2 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 action: return origin, host, and path for a URL, and explicitly drops query and fragment. This is clear and distinct, though it does not name sibling tools to differentiate. The verb and resource are precise, so it earns a 4 rather than 5.

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

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

No guidance is given about when to use this tool versus the many URL-related siblings (e.g., browser-url-ok, fetch-status, domain-shape). There is no mention of alternatives, exclusions, or context where this tool is preferred. The description implies a simple normalization use case but does not explicitly state 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?

With no annotations, the description carries the full burden of behavioral disclosure. It only repeats the unit names and provides no information about what the tool does, what it returns, or how it handles inputs. There is no mention of side effects, limitations, or required inputs.

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. It is a single phrase that adds no actionable information. There is no structure or front-loading of key details because there are none.

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 annotations, and no output schema, the description is drastically incomplete. An agent cannot infer how to call the tool, what input to provide, or what output to expect. The description fails to provide even the minimal context needed 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?

The schema lists 9 parameters with descriptions that are unrelated to pressure conversion (e.g., 'Git ref name', 'HTTPS URL', 'City name'). The description adds no clarification on which parameter represents the pressure value or how the conversion is performed. Even though schema coverage is 100%, the schema itself is misleading and the description does not compensate.

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 'Pascals to bar' is essentially the tool name restated as a noun phrase, offering no verb or action. It does not state what the tool does, such as 'Converts a value from Pascals to bar.' It fails to differentiate from siblings and is a tautology.

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 28 siblings. There is no mention of intended context, prerequisites, or alternatives. The description gives the agent zero direction for tool selection.

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

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

With no annotations, the description carries the full burden, but it only discloses that no browser is launched. It doesn't say whether a network request is made, what happens if the URL is unreachable, or what the return value is. The parameter descriptions hint at 'shape check' and discarding inputs, but this is vague and not tied to the stated URL-checking behavior.

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

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

The description is brief (two sentences) and front-loads the core action, but it is under-specified for a tool with nine parameters and no output schema. Conciseness is not a problem, but the lack of structure or detail makes it minimally 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 nine optional parameters, no output schema, and no annotations. The description does almost nothing to explain what the tool actually does with these parameters, what it returns, or how to interpret results. This is severely incomplete for an agent to correctly invoke the tool, especially given the mismatch between the description and 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 the baseline is 3, but the parameter descriptions are confusing and unhelpful. They say things like 'discarded after the shape check' or 'titles discarded,' but don't explain how these relate to checking if a URL can be opened. The agent cannot determine which parameter to supply for the stated purpose, especially since the tool name suggests only a URL 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 states a clear verb and resource: 'Check whether a URL can be opened.' However, the input schema exposes nine unrelated parameters (city, feed, json, path, zone, query) with descriptions implying a broader shape-checking role, so the stated purpose does not match the schema. It also doesn't differentiate from the sibling 'browser-url-ok' beyond a hint that no browser is launched.

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 only usage hint is 'No browser is launched,' which implies this is for lightweight checks without a browser, but it doesn't explicitly say when to prefer this over browser-url-ok, normalize-url, or web-fetch. No exclusions or alternative names are provided, leaving the agent to guess the appropriate context.

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

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

With no annotations provided, the description must carry the full burden of behavioral disclosure, but it reveals nothing beyond being a 'catalog'. It doesn't state whether the tool is read-only, what it returns, how inputs are used, or what side effects occur. The schema hints at shape checks, but the description doesn't confirm any behavior, making it highly opaque.

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

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

The description is a single short sentence, which is efficient in length but under-specifies entirely. It lacks any structure that front-loads purpose or usage, and its brevity is not a virtue when it omits critical information. It is not an appropriately sized description for a tool with nine parameters.

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

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

The tool is complex (9 parameters, no output schema, no annotations), yet the description is a bare noun phrase. It does not explain what the tool does, how inputs relate to outputs, what the expected response format is, or any constraints. The description is wholly inadequate for an agent to call this tool correctly.

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

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

Schema coverage is 100%, so the parameter descriptions exist, but the tool description adds no semantic linkage between the parameters and the stated purpose. The parameter descriptions (e.g., 'discarded after the shape check') suggest the tool performs validation, yet the description says it's a status-code catalog, creating a mismatch. The description fails to clarify how these parameters map to the tool's function.

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

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

The description 'Short catalog of common HTTP status codes' is a noun phrase, not a clear verb+resource. It doesn't state what the tool does with its nine input parameters, which are described as shape checks or discarded values in the schema. The name suggests a status-code reference, but the parameters imply a different purpose, making the intent vague and confusing.

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

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

No when-to-use guidance is provided. The description gives no indication of when to select this tool over any sibling (e.g., fetch-status, browser-url-ok). There are no alternatives, exclusions, or context cues, 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 are provided, so the description carries the full burden. It explicitly says 'Prompt discarded' and each parameter description notes 'discarded after...', which transparently discloses that inputs are ignored. This is important behavioral info, but it does not describe what the template contains or any side effects (likely none). Given the simplicity, this is adequate but not deeply rich.

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

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

Two short sentences with no waste. The key behavioral fact (inputs discarded) is front-loaded in the first sentence, and the second sentence reinforces it. 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 trivial tool that returns a fixed template, the discarding behavior is clearly explained. However, it never describes what the three-step template actually contains, which could be relevant for an agent deciding whether to call it. With no output schema, the agent is left guessing about the return value's content. A bit more detail on the template's purpose or structure would make it complete.

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

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

Schema description coverage is 100%, but the description adds the crucial fact that each parameter is discarded after the shape check or call. This goes beyond the schema's type-only descriptions, informing the agent that no input actually affects the result. Since no parameters are required, the agent knows they can pass anything or nothing. This is valuable semantic clarification.

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 'Return a three-step thinking template' with a clear resource. The verb 'return' and resource 'template' are unambiguous, and the tool is clearly distinct from siblings like fetch-status or validate-json which perform checks. No confusion about what this tool does.

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

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

No guidance on when to use this tool versus alternatives. It does not mention any context where a three-step thinking template would be helpful, nor when to avoid it. The only hint is that inputs are discarded, but that doesn't help an agent decide to invoke it. Lacks any 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the output ('current time') without mentioning that only the 'zone' parameter is relevant, that other parameters are ignored, or any response format. For a simple lookup this is minimal but not 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 a single sentence, which is concise, but it under-specifies the tool given the large number of parameters and the existence of related siblings. It is efficient but not informative enough for the complexity involved.

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 but only one relevant, and there is no output schema or annotation coverage, the description is incomplete. It does not explain that other parameters are ignored, what the response looks like, or how it relates to utc-time and iana-zones, making it inadequate for confident 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?

The schema has 100% coverage, so the baseline is 3, but the description does not clarify which of the 9 parameters actually affects the call. The schema descriptions are clear for each parameter, but the tool description fails to highlight that only 'zone' matters, leaving the agent to figure out the intended usage among many irrelevant 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 the current time in a named IANA timezone, which is a specific verb+resource. However, it does not explicitly differentiate from sibling tools like utc-time or iana-zones, leaving some ambiguity about 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?

There is no guidance on when to use this tool versus alternatives. Sibling tools like utc-time and iana-zones exist, but the description does not mention them or any selection criteria, so the agent must infer usage.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It only states the output (a timestamp) and says nothing about how the input parameters are handled, whether they are validated, discarded, or ignored. The schema's parameter descriptions mention 'discarded after the shape check', implying a validation step that the description omits, leaving the tool's actual behavior opaque.

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

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

The description is a single, clear sentence with no filler. It front-loads the core purpose immediately. This is maximally concise and efficient for the information it conveys.

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

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

With 9 optional parameters and no output schema, the description is grossly incomplete. It fails to explain why these parameters exist, what happens if they are provided, whether the tool performs validation, or what the response format is. An agent cannot confidently call this tool with the given 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%, and each parameter already has a detailed description explaining its purpose and that it is discarded after a shape check. The tool description adds nothing about parameters, which is acceptable given the schema's completeness. However, it does not resolve the mismatch between the timestamp purpose and the parameter descriptions, so it neither enhances nor detracts from the schema's 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 clearly states the tool returns the current UTC timestamp, a specific verb+resource. However, the input schema includes 9 optional parameters with descriptions implying shape checks and discarding behavior, which is not reflected in the description. This creates ambiguity about whether the tool does more than return a timestamp, so it is not fully distinct from its 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 versus alternatives like 'timezone' or 'iana-zones'. There is no mention of prerequisites, exclusions, or context for selection. An agent receives zero routing information.

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 does state that 'the body is discarded,' which indicates a non-persistent, safe operation. However, it fails to disclose the return format (e.g., boolean success/failure), error handling, or whether the 'json' parameter is the actual input. The minimal disclosure is not enough for a tool with no annotations.

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—and front-loads the core purpose in the first sentence. Every word earns its place, with no filler. However, its brevity sacrifices essential usage details, making it under-specified rather than appropriately concise, so it falls short of a perfect 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?

For a tool with nine optional parameters, no output schema, and no annotations, the description is woefully incomplete. It does not specify which parameter holds the JSON to validate, what the tool returns, or how to handle invalid JSON. An agent would be unable to reliably invoke this tool without additional context. The absence of any usage or return information 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?

The schema descriptions provide 100% coverage, clearly explaining each parameter's purpose (e.g., 'JSON text to validate; discarded after the check'). The tool description adds no extra meaning beyond the schema, except the ambiguous 'body' reference. Since the schema already does the heavy lifting, the baseline of 3 is appropriate, but the description fails to clarify which parameter is the 'body,' so no additional value is contributed.

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 verb (check) and resource (JSON validity), distinguishing it from sibling tools since none other explicitly validate JSON. However, the term 'body' is ambiguous—the schema has a 'json' parameter but also many others, so it's not immediately clear which input is being validated. This slight ambiguity prevents a perfect score.

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 instruction on which parameter to populate. With nine optional parameters and no required fields, an agent has no idea which one to set. There is no mention of exclusions or typical use cases, leaving the tool unusable without further 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 are provided, so the description must carry the full behavioral burden. It only states the action without disclosing that it makes a network call, that other parameters are discarded, that results are ephemeral, or any failure modes. The description adds minimal behavioral context beyond the bare 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 a single, front-loaded sentence with no wasted words. It is appropriately concise, though it sacrifices necessary detail. Structurally it is easy to parse, but the brevity comes at the cost of completeness.

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

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

Given the tool has 9 optional parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain which parameters are actually used, how to construct a valid call, or what the response will look like. The context is far too sparse for an agent to use the tool correctly.

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

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

The schema has 100% description coverage, but most parameter descriptions are irrelevant to the tool's purpose (e.g., 'Git ref name', 'HTTPS URL', 'JSON text'). The tool description does not clarify that only 'city' matters, nor does it explain how to use the parameters. This is a case where the schema is misleading and the description fails to compensate, so a score below baseline is warranted.

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

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

The description clearly states the verb (get current temperature) and resource (a city via Open-Meteo). It is specific enough to convey the core function, though it does not differentiate from sibling tools like 'geo-hint' or 'timezone' that might also involve location or weather-adjacent data. The description is not a tautology but could be more explicit that only the 'city' parameter is relevant.

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

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

There is no guidance on when to use this tool versus alternatives. No mention of prerequisites, such as needing a valid city name, or exclusions like 'not for weather forecasts.' The agent is left to infer usage from the description alone, which is insufficient.

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

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

With no annotations, the description carries full responsibility for behavioral disclosure. It only mentions 'Body discarded' but omits other important traits like read-only nature, potential network access implications, or any side effects. The schema descriptions note parameters are 'discarded', but the description itself is minimal.

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

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

The description is a single sentence with zero wasted words, front-loading the core purpose. It is appropriately concise, though it could arguably be slightly more detailed without becoming bloated.

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. The description is far too brief to cover what each parameter is for, how the response is structured, or any operational constraints. It only covers the URL fetching aspect, leaving the rest unexplained.

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 meaningful description in the schema. The tool description adds nothing about parameters, but per the calibration baseline, a score of 3 is appropriate when the schema fully documents 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 fetches a URL and returns HTTP status and content type, with a specific verb and resource. However, it does not differentiate from siblings like fetch-status, which likely performs a similar function, so it lacks sibling 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?

The description provides no guidance on when to use this tool versus alternatives such as fetch-status, browser-url-ok, or normalize-url. There is no mention of conditions, exclusions, or alternative selection criteria.

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