User-Agent length, value discarded

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

With no annotations, the description is fully responsible for behavioral disclosure. It adds 'task text discarded' and 'returns connection methods', which are useful transparency signals. However, it does not say whether network calls occur, what the returned connection-method format is, whether there are costs, or any authentication expectations.

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?

Three short sentences with no waste: purpose, return value, and the task-text disposal caveat are in order. Every sentence earns its place, and key meaning is front-loaded.

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 9-parameter, no-output-schema, no-annotation tool, the description gives the basic contract but not complete information: the result format of 'connection methods' and how parameters shape the lookup are left unspecified. It is adequately helpful for a task but not complete enough to be fully autonomous on a novel input.

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

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

The schema carries 100% description coverage, so the baseline is 3 and the description doesn't need to restate parameter types. It adds only a loose mapping between task examples and parameters; the description doesn't clarify how each parameter contributes to gateway discovery. This is sufficient but not enriching.

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 opens with a specific verb and resource ('Find a public pay-per-call tool gateway'), then gives concrete example tasks (weather, search, scrape, voice). It clearly differentiates this as a discovery/index tool rather than a direct utility, though it doesn't name which sibling it replaces.

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?

Usage is implied through the example task list and the promise of returning connection methods, which tells an agent the kind of task this tool is for. There is no explicit exclusions like 'use X for Y instead', so the agent must infer selection from the description and sibling names.

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 carries the full behavioral burden. It discloses that no browser is launched, which is useful safety context, but it does not state whether a network request is made, whether the operation is read-only, what the return value looks like, or what kind of error may occur. This leaves meaningful uncertainty for the agent.

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 tight and front-loaded: purpose comes first, then the main behavioral distinction. There is no fluff. It loses a point because it is too thin relative to a 9-parameter tool, but as a concise definition it 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?

Given 9 optional parameters, many overlapping sibling tools, no output schema, and no annotations, a two-sentence description is far from complete. The agent is left without knowing what response to expect, how to specify the URL being checked, or how this tool differs from the many other checkers/utilities listed as siblings.

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

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

Schema description coverage is 100%, so the schema already documents each of the 9 parameters. The description adds no parameter-specific meaning, but the baseline is still 3 because the parameter burden is already carried by the schema. However, the description also fails to indicate which of the 9 optional parameters matter for the core URL-openability check, and the schema's 'url' description says 'normalize or cite' rather than 'open'.

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: it checks whether a URL can be opened. It also adds a useful qualifier, 'No browser is launched', which distinguishes it from browser-based siblings like playwright-url-ok. It is not a 5 because 'can be opened' is not fully defined, and older agents may wonder whether this is a syntax check or a network probe.

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 explicit when-to-use versus alternative guidance. The description does not mention playwright-url-ok, fetch-status, domain-shape, or other siblings, and it does not explain when the agent should choose this tool over them. The only indirect clue is 'No browser is launched', which is insufficient guidance.

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

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

'Expression discarded' hints that inputs are not persisted, but this does not explain actual behavior: whether validation occurs, whether network access happens, what is returned, or why the listed parameters are accepted. With no annotations provided, the description carries the full burden and fails to disclose the tool's real 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 text is only two short sentences, but brevity here is under-specification, not conciseness. The critical information is not front-loaded in a useful order, and 'a+b style' is a confusing non-standard way to state the tool's scope.

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 completely unrelated parameters, no output schema, and no annotations, this description is severely inadequate. It explains none of the parameters, no return value, no failure behavior, and no indication of what distinguishes it from its many siblings. An agent has essentially nothing reliable to go on.

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 description adds no meaning about how these nine parameters relate to the tool's purpose. Worse, the description's arithmetic framing actively conflicts with the parameter set (none are arithmetic expressions). The description fails to justify or unify the 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 names a verb and resource ('Evaluate a+b style arithmetic') but the input schema contains nine string parameters (ref, url, city, json, zone, query, etc.) that have nothing to do with arithmetic. An agent cannot tell what this tool actually operates on, and none of the sibling tools are referenced for differentiation. The phrase 'Expression discarded' adds confusion rather than 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 guidance is given about when to call this tool versus any of the 27 siblings. There is no context for conditions, exclusions, or alternatives. An agent has no basis to choose this over tools with similar-sounding shape-check purposes.

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

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

Annotations are absent, so the description carries the behavioral burden. It does disclose one meaningful behavior: 'Page content is not stored.' That suggests a privacy/read-only quality, and 'Return' implies a read operation. However, it does not address handling of the many extra parameters, potential side effects, errors, or permission requirements, leaving a clear transparency 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 short and front-loaded: the main purpose appears in the first sentence and the behavioral note in the second. There is no fluff, but the brevity sacrifices context needed to handle the parameter-rich schema.

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

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

This is a 9-parameter tool with no output schema and substantial sibling overlap. The description only explains a URL-shaped use case and leaves the other parameters unexplained in the tool-level description. It is not complete enough for an agent to confidently invoke the tool across the full schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no new parameter meaning beyond 'URL', which maps to the 'url' property. It does not explain how to use the other 8 optional parameters or clarify which ones are needed to satisfy the stated purpose.

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

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

The description states a specific outcome: 'Return host, scheme, and HTTP status for a URL.' It uses a clear verb and resource, and the additional 'Page content is not stored' hints at scope. However, it does not differentiate this from similarly named siblings like fetch-status, normalize-url, or domain-shape, so an agent may not know why citation is the right choice.

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

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

No guidance is given about when to use this tool versus sibling tools. There is no mention of alternatives, disqualifying conditions, or which of the 9 optional parameters should be present for the tool to be meaningful. An agent is left to infer that 'url' is the primary parameter, but the description does not say so.

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 partly carries the behavioral burden and does disclose a privacy-relevant trait: 'No identifiers are retained.' Parameter descriptions reinforce non-retention and no-disk-access behavior, but the description does not state whether the tool is fully read-only, whether it makes network calls, or what it consumes/emits.

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

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

The two-sentence description is short and front-loaded, but it is more under-specified than genuinely concise. Each sentence pulls its weight, yet the core purpose and behavior remain too thin for a nine-parameter tool.

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 required output schema, so the description itself must explain what the classification result looks like; it does not. With nine optional parameters, zero annotations, and no return-value explanation, the definition is not sufficient for an agent to use the tool confidently.

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

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

Schema description coverage is 100%, so the baseline is 3 even though the main description adds no parameter detail. The property descriptions are individually meaningful but the tool description itself does not explain how the many optional parameters affect classification.

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 generic resource ('show how this request is classified'), so it is not a pure tautology. However, it does not specify what classification labels/outcomes are returned or how this differs from the many other classification/checking tools among the 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?

There is no stated guidance about when to call this tool versus sibling tools like validate-json, geo-hint, timezone, or fetch-status. No prerequisites, exclusions, or alternative-selection conditions are provided.

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 carries the transparency burden. It clearly indicates a pure syntactic operation with no WHOIS/ownership lookup, which strongly implies no external data fetch. It does not explicitly discuss output or side effects, but the behavior is unusually well scoped for a string-splitting tool.

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

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

One clean, front-loaded sentence states the action and the key non-behavior. There is no wasted wording or duplicated schema content.

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

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

The description and schema cover the core shape-check operation, but the nine optional parameters and the lack of an output schema leave room for ambiguity about what an agent actually needs to pass and what the result looks like. Complete enough for a trivial utility, but not fully self-contained.

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

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

Schema description coverage is 100%, so the schema already documents all 9 parameters. The description adds general hostname-label intent but does not clarify how the many optional non-host parameters relate to the operation; therefore the baseline of 3 is appropriate.

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

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

The description states a specific operation—'Split a hostname into labels'—and immediately clarifies the boundary with 'without WHOIS or ownership data.' This distinguishes it from lookup-style siblings and other shape tools such as github-repo-shape 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?

The exclusion of WHOIS/ownership data gives an implicit usage boundary, but there is no explicit 'use this when…' or 'use X instead when…' guidance. An agent can infer intended use but must rely on sibling names to route 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, the description carries the full transparency burden. It mentions the HTTP method and the public URL requirement, but it does not disclose what happens with the remaining eight parameters, any rate limits or authorization constraints, or what 'status only' covers. Some schema entries say values are 'discarded after the check', but the description itself leaves that behavioral reality out.

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

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

One short, front-loaded sentence with no wasted words and no redundancy against the schema. It is as concise as a tool description can be, though the conciseness is partly why it lacks broader guidance.

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 output schema, and no annotations, one line about HEADing an URL is far from complete. It does not explain what the various fields represent, how the return status should be interpreted, or when non-URL parameters are relevant.

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 full 100% parameter descriptions, so baseline is 3, but the description adds little and actually aligns poorly: it frames 'url' as a HEAD target, while the schema's url description says 'HTTPS URL to normalize or cite'. It gives no guidance on the other eight params and therefore makes correct invocation of non-URL scenarios harder.

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 gives a specific action, resource, and output: HEAD a public URL and return status only. It also implicitly distinguishes this from full-content that might be expected from web-fetch or browser tools, though it does not account for the wide range of parameters in 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?

There is no explicit guidance about when to use this tool versus siblings, and no exclusions such as 'for full content use web-fetch' or 'for browser rendering use playwright-url-ok'. The only hint is 'status only', which is not enough for an agent to route among the many similar 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?

Annotations are absent, so the description must carry the full burden. It only says 'path discarded,' which is a hint but not enough to disclose side effects, read-only behavior, error handling, or return values. It does not explain what the tool does with the URL or whether it modifies any state. The hint is ambiguous; it could mean the URL path component is ignored, or the 'path' parameter is 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 short and the main action is front-loaded, but the brevity is more under-specification than good conciseness. It lacks the necessary details to be a complete, reliable description, so it does not earn a high score on this dimension.

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 agent needs a more detailed explanation of the return value, expected input format, and any edge cases. The description provides almost none of that; it is insufficient for safe and 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 coverage is 100%, so the baseline is 3. The description adds the import that the tool is about parsing a URL, implying the 'url' parameter is the primary input and potentially that paths are not used. However, it does not explicitly tie the description to the parameter names, and the ambiguity of 'path discarded' leaves room for confusion with the 'path' parameter in 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 brief statement 'Parse a Figma file URL. Path discarded.' does identify a resource (Figma file URL) and a verb ('parse'), but it doesn't explain what 'parse' yields or how it differs from the similar sibling tools like normalize-url or browser-url-ok. It's not a complete tautology, but it is vague about the tool's core behavior.

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 call this tool instead of a sibling, nor what conditions should hold (e.g., valid URL formation, required parameters). The description gives no use-case context, exclusion case, or alternative routing.

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

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

'No disk access' is a useful, truthful behavioral guarantee, and it is the only non-obvious information provided. However, since annotations are absent, the description carries the full burden of disclosing side effects and semantics. It never explains that the other eight schema parameters are discarded or ignored, nor what the return value looks like, nor whether the tool can be called multiple ways. The disclosure is too incomplete for this operation.

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, no filler, and the key non-obvious behavioral fact ('No disk access') is front-loaded only once. Every word earns its place. The issue is under-specification, not verbosity, and conciseness should be judged separately from 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?

A 9-parameter, zero-required tool with no output schema and no annotations cannot be correctly used based on a two-line description. The writer does not explain the winner—the 9 params and the shape-check tool's role among 27 siblings—nor what the result means. The description is wildly insufficient for the actual task-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% and each parameter has a description, so the heavy lifting for parameter meanings is done by the schema. The tool description adds no parameter-level semantics except the general 'path' hint, and it conspicuously fails to explain why the tool accepts parameters like city, feed, and query that are unrelated to the stated purpose. Baseline of 3 is appropriate due to high coverage, but this is not a positive contribution.

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 verb ('check') and a resource ('whether a path looks safe'), so it is not a tautology. However, after reading it, an agent cannot know which of the tool's nine parameters are relevant, because the schema also accepts ref, url, city, feed, host, json, zone, and query. The description's single-purpose wording conflicts with the broad schema and does not clearly differentiate it from its many sibling 'shape-ok' 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?

The description gives no guidance on when to call this tool, when not to, or what to use instead. Given 27 sibling tools like browser-url-ok, domain-shape, and wiki-title-shape, an agent has no way to know whether file-path-ok is the right choice. It also omits the condition mentioned in the schema e.g., that all parameters are optional but which one should be passed for what scenario.

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 of behavioral disclosure. It only states the function; it does not mention network calls, read-only nature, side effects, or what happens to inputs (though some schema descriptions mention discarding, that is not in the description). The behavior is 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, front-loaded sentence that immediately states the purpose. It is concise and wastes no words.

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, none required, and no output schema, the description is severely incomplete. An agent has no idea which parameter to supply, what the tool expects as input, or what the return format looks like. The minimal description is insufficient for a tool with this many parameters and no structured guidance.

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 beyond the schema—it does not explain how the 9 parameters relate to the 'place' or which one to use. It neither improves nor harms parameter understanding beyond the schema.

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

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

The description states a clear purpose: returning latitude and longitude for a place using Open-Meteo. It is not a tautology and gives a specific resource. However, it does not specify which input parameter identifies the place, nor how it differentiates from sibling tools like weather-hint, 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?

The description offers no guidance on when to use this tool versus alternatives. There is no mention of preferred parameters, context, or exclusions. An agent cannot tell whether to pass 'city', 'query', or another field, and no sibling comparison is made.

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 says only that the tool parses owner and repo. This implies a read-only action, but it does not disclose whether parameters are discarded, what happens on invalid URLs, or whether any side effects occur. With no annotations, the description leaves the safety profile and failure behavior entirely to the agent's imagination.

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 short sentence, and the purpose is front-loaded. It is exactly what a terse tool description should be, though it sacrifices detail 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?

The description is radically incomplete for a tool with 9 optional parameters and no output schema. It does not say what the parsed output looks like (e.g., an object with owner and repo), does not explain error behavior, and does not clarify which parameters are relevant. An agent could not reliably decide how to invoke the tool from this definition 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?

Although the input schema has 100% parameter description coverage, all parameters are optional strings with conflicting roles. The single description line does not specify which parameter is expected to hold the GitHub URL, nor how the other 8 parameters should be treated. The schema alone is not enough, and the description fails to disambiguate the intended input.

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 task: 'Parse owner and repo from a GitHub URL.' This is a specific verb and resource, and the GitHub focus helps distinguish it from sibling domain/figure/Jira shape tools. However, it does not explicitly differentiate itself from generic URL tools like normalize-url, so it stops short of a 5.

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

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

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'from a GitHub URL' only implies the use case, but the description does not specify which of the 9 optional parameters to supply, nor does it mention when not to use this tool or suggest siblings. This is close to no guidance at all.

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 adds the useful behavioral note that titles are discarded and only the count is relevant, but it does not explicitly disclose whether this is a safe read-only operation, whether it fetches live data, or how errors/timeouts behave. Without annotations, the description carries the burden and barely meets it.

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

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

Two short sentences deliver the core purpose and the key output limitation with no filler. This is properly front-loaded and 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?

It is enough for a simple count request, but the description does not clarify how to call the tool when there are nine optional parameters, and there is no output schema to confirm the exact return format. The odd param list is only understood by reading inline schema descriptions.

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, and the description adds no meaningful parameter semantics. The schema already explains the parameters as validation-only/discarded values, but the tool description does not clarify which parameter, if any, actually influences the HN count.

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?

Purpose is stated with a specific verb and resource: 'Count current Hacker News front-page stories.' The addition 'Titles discarded' clarifies the output contract, making it distinct from fetch-style siblings like web-fetch or fetch-status.

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

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

There is no explicit guidance on when to use this tool vs alternatives, no required parameter note, and no statement that all parameters can be ignored. An agent is left to infer the intended call pattern from the purpose sentence 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?

There are no annotations, so the description carries the full burden of disclosing behavioral traits, but it says nothing about side effects, return values, or whether the operation is read-only. Although the input schema descriptions hint that several fields are 'discarded after the check' and mention 'no disk access,' those are in the schema, not the tool description. The description completely omits any behavioral information on its own.

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 a single short sentence with no wasted words, so it is concise. However, it is under-informative and not front-loaded with an actionable purpose; it reads more like a label than a tool description, making it acceptable but not a model of efficient communication.

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 required fields, no output schema, and zero annotations, the description does not provide enough context for an agent to know what the tool does when invoked. It fails to explain the relationship between the many parameters and timezone zones, or what the tool returns, making it inadequate even as a minimal operational summary.

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 (100% coverage), so the baseline is 3; the tool description adds no parameter-level meaning beyond the schema. It vaguely relates to timezone zones but does not clarify how the many unrelated parameters (ref, url, city, feed, host, json, path, query) fit with an IANA-zone lookup, so it neither enriches nor contradicts 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 is a noun phrase ('Common IANA timezone names for clock calls') that largely restates the tool name and does not state an operation (e.g., list, return, validate, or transform). It adds that the names are for clock calls, but an agent cannot tell whether this tool outputs a list, checks a zone, or is a validation rule, and it does not differentiate it from the sibling 'timezone' tool.

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' provides a minimal implied usage context, suggesting it should be used when IANA timezone names are needed for clock-related operations. However, it does not list any alternatives, exclusions, or conditions, so it is closer to simply implying a use case than giving explicit routing guidance.

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

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

Annotations are absent, so the description carries the full burden of disclosing behavior. It states that the tool fetches a public robots.txt and returns group counts only, but it does not explain how errors are handled, what happens when a robots.txt is missing, whether output is structured in a particular way, or how the URL is supplied. These are significant ambiguities for a network-accessing tool.

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

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

The description is a single, efficient sentence with no filler. It is front-loaded with the core action and the 'only group counts' qualifier. It is concise, even if it is not fully informative for the 9-parameter schema.

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

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

The tool has a history of 9 parameters, zero required parameters, no output schema, and no annotations. The description does not explain the parameter-vs-action mapping, the meaning of 'group counts', the output format, or error behavior. In this context, the description is not complete enough for an agent to invoke the tool correctly without extensive trial and error.

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 covers all 9 parameters with descriptions, so the baseline is 3 per the rubric. The tool description itself adds little parameter-level meaning: it does not explicitly say that the 'url' parameter is the robots.txt location, nor does it clarify why other parameters exist. However, there is no direct contradiction, and the schema descriptions bear most of the load.

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 what the tool does: fetch a public robots.txt and return only group counts. The resource and output are specific, and this differentiates it from generic fetching tools like web-fetch or fetch-status, which would return full content or statuses rather than group counts.

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 siblings such as web-fetch or fetch-status, nor any explicit conditions, exclusions, or alternatives. The behavioral scope has to be inferred from the one-line description, leaving the routing decision entirely to the agent.

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

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

Annotations are absent, so the description carries the full behavioral burden. It discloses only that the key is 'discarded,' which is a useful privacy note, but it does not state the return value, validation criteria, error behavior, or whether the tool only reads input without 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 very short, but it is under-specified rather than concise. The second sentence, 'Key discarded,' adds only a vague behavioral note and does not replace the missing explanation of how to call the tool.

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 annotations, and no output schema, this description is far too thin. It does not define what 'shape' means, which parameter to pass, what result to expect, or how this tool fits among the many sibling validators.

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 normally earns a baseline of 3, but the description introduces a 'key' concept that maps to no schema property. With nine optional parameters and no indication of which one is the Jira issue key, the description actively fails to add insight 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 specific action and resource: 'Check a Jira issue key shape,' which distinguishes it from sibling shape-checking tools. However, it never ties that purpose to a parameter, since no schema property is named 'key'; the agent is left guessing which input carries the Jira issue key.

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

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

There is no guidance on when to use this tool over siblings such as domain-shape, github-repo-shape, or wiki-title-ok. The description does not explain which input scenarios call for a Jira key shape check.

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 transparency burden. It discloses that the body is discarded, but it does not describe the HTTP method, status/error behavior, how the other eight parameters are handled, or what happens when none 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 compact and front-loaded: two short sentences, no filler. The body-discarded detail is useful and earns its place.

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

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

For a tool with nine optional parameters, no annotations, and no output schema, this is far from complete. It does not explain how the other parameters are used, what format the status is returned in, or how an agent should decide which parameter to pass.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds a small amount of meaning to the url parameter, but it does not help the agent understand the purpose or role of the many unrelated optional parameters such as city, zone, feed, or json.

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 concrete action and resource: return an HTTP status for a public library docs URL while discarding the body. It is not a tautology, and the 'body discarded' detail helps separate it from a full fetch tool, though it does not explicitly contrast itself with siblings like fetch-status or browser-url-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 on when to use this tool instead of fetch-status, web-fetch, normalize-url, or browser-url-ok. The statement 'body discarded' hints the body is not needed, but no conditions, exclusions, or alternative tools are named.

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 behavioral burden. 'Values discarded' is a useful disclosure that values are not retained in the result, but the description does not clearly state whether this is read-only, whether it has side effects on memory, or what the return value communicates beyond a count.

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

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

The description is very concise, front-loaded, and free of filler. Most words add value, but slight confusion around 'JSON object' in relation to the supplied schema could have been removed with a short clarifying clause.

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, this description is under-specified. It does not say which input represents the JSON object, how to construct the object, or what the count value should be interpreted as, leaving the agent to infer major parts of the contract.

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 input schema already documents all nine parameters, giving a baseline of 3. The description adds the 'values discarded' semantic but does not explain how the declared flat parameters correspond to a JSON object or which parameter is the intended object to count.

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 keys in a JSON object — and adds a clear behavioral note that values are discarded. It is not explicitly differentiated from sibling tools such as validate-json, but the counting purpose is recognizable and distinct at a high level.

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

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

There is no guidance about when to use this tool versus alternatives, no context for selection, and no exclusion of when it should not be used. Siblings like validate-json or shape tools are not referenced, so the agent receives no 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?

Annotations are absent, so the description carries the behavioral disclosure burden. It does disclose a meaningful behavior: 'Query and fragment are dropped,' and it states the output scoped to origin, host, and path. Still, it does not describe what happens if no valid URL is supplied, whether any validation is performed, or the exact output format. This is adequate but incomplete for a no-annotation tool.

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

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

The description is two crisp sentences that lead with the core behavior and mention the main side-effect behavior immediately. There is no fluff or repetition; every sentence earns its place.

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

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

Given the tool has 9 optional parameters, no output schema, and no annotations, the description is only partially complete. The schema compensates with per-parameter descriptions, but the tool description itself still leaves the agent to puzzle out which parameter actually matters. A note like 'Provide the url parameter; other parameters are ignored' would make this 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%, so the baseline for this dimension is 3. The tool description does not add parameter-level meaning, but the 'url' parameter description is explicit. However, many unrelated parameters (city, zone, json, ref, feed, etc.) with 'discarded' behavior are present, and the tool description does nothing to highlight that only the 'url' 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 clearly states a specific action and resource: 'Return origin, host, and path for a URL.' The behavior of dropping query and fragment also distinguishes it from mere URL validators like browser-url-ok or fetch-status. However, it does not explicitly reference any sibling alternatives, so it earns a 4 rather than a 5.

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

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

The description gives no guidance on when to use this tool instead of similar URL-related tools, no prerequisites, and no mention of which input is the primary URL. It only says what it does, not the context that selects 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?

No annotations are provided, so the description carries the full burden. It discloses 'No browser is launched,' which is useful, but it does not cover return format, network access, timeouts, failure modes, or how the many 'discarded' parameters affect behavior. This is a significant atax for a tool with no annotation safety profile.

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, no fluff, front-loaded with the core action. The statement 'No browser is launched' earns its place by dispelling a likely expectation for a Playwright-related tool. It could offer more detail, but the conciseness dimension rewards 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?

The tool has 9 optional parameters, no output schema, and no annotations, yet the description is minimal. The schema describes each parameter, but names like 'ref', 'city', 'zone', and 'query' suggest a broader shape-check capability that the description does not reconcile. An agent cannot confidently determine what parameters actually matter or what the return value looks like.

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

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

Schema description coverage is 100%, and each of the 9 parameters has its own description. The tool description itself adds no parameter-level meaning beyond the schema, so the baseline of 3 applies.

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: 'Check whether a URL can be opened' and adds a meaningful caveat, 'No browser is launched.' This is clear for a URL-checking tool, though it does not explicitly differentiate from sibling tools like browser-url-ok beyond the no-browser trait.

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 name sibling tools, specify when to use it instead of a fetch or browser-launching tool, or mention any exclusions. The agent must infer usage from the name and one-line description.

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

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

With no annotations, the description carries the behavioral burden and it does disclose that the query is discarded. However, most of that disclosure is already present in the `query` parameter schema ('discarded after the length check'), so the tool description adds limited transparency beyond the structured fields and does not mention return value semantics 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 two short sentences with no filler. The primary action is front-loaded and the side-effect note is immediately after it.

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, none required, no annotations, and no output schema, but the description does not explain which parameter to use or what the output shape is. It also leaves ambiguous why the other optional fields exist, which hurts an agent's ability to invoke the tool confidently.

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

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

Schema description coverage is 100%, so the baseline is 3. The phrase 'Count characters in a search query' does not add meaning beyond the schema, and it does not clarify how the 8 other optional parameters relate to the tool or whether `query` is the intended one.

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: count characters in a search query. It also adds a side-effect note that the query is discarded. It loses a point because it does not distinguish this from count/shape sibling tools or clarify which of the nine schema parameters constitutes the 'search query'.

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 alternatives such as memory-key-count, hn-front-count, or normalize-url. The sentence 'Count characters in a search query' describes the operation but not the selection context or when-not-to-use conditions.

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 behavioral burden. It says the result is a short catalog, but it does not state what is returned, whether any argument is needed, whether the catalog is filtered by the input parameters, or that the operation is side-effect free.

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

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

The description is a single, front-loaded sentence with no filler or repetition. It is concise, although the brevity veers toward under-specification rather than efficient 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?

For a tool with nine optional parameters, no annotations, and no output schema, this description is too sparse. It does not say why the parameters exist, whether they filter or affect the catalog, what the returned structure looks like, or that the tool can simply be called with no arguments.

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

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

Schema description coverage is 100%, so each parameter already has a property-level description and the baseline is adequate. The tool description adds no connection between those nine optional parameters and the HTTP status catalog, but per the rubric the high schema coverage keeps this at the baseline.

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

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

The description names a concrete resource (common HTTP status codes) and a catalog-like purpose, so an agent can broadly understand the tool's topic. However, it uses no specific verb, ignores the tool's 9-parameter schema, and does not distinguish itself from siblings such as fetch-status or web-fetch.

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

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

There is no guidance about when to use this tool instead of a sibling, how many parameters should be supplied, or what kind of request should be routed here. The description implies it is a reference catalog but never states the intended call pattern.

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 burden. It states the prompt is discarded, but fails to disclose whether parameters are validated, what the output contains, or any failure modes. This leaves substantial ambiguity in its 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?

One sentence, no fluff. Extraneous details are omitted, but the core function is communicated efficiently.

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

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

Despite simple, the tool has a 9-parameter optional schema, no output schema, and no annotations. The description doesn not clarify whether the printed parameters are entirely ignored, whether any should be provided, or what the return value looks like, leaving an agent uncertain.

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 itself adds no parameter-level semantics. Schema coverage is 100% as all parameters are described in the schema, so the baseline 3 applies.

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 'Return a three-step thinking template' with a clear verb and resource, and 'Prompt discarded' distinguishes it from tools that analyze input. It doesn't specify what the template looks like, differentiating it slightly from a pure 5.

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

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

There is no guidance about when to use this tool, conditions that trigger it, or any alternative tools. The description gives no usage context at all.

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 carries the disclosure burden. It names the outcome and read-like nature of the operation, but it doesn't disclose invalid zone handling, return time format, or whether the input is normalized. This is acceptable for a simple lookup but not fully transparent.

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

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

A single sentence with no filler wordiness. Every word is necessary, and the core purpose is front-loaded.

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?

Without an output schema or annotations, the description only covers the tool's one-line intent and doesn't mention result structure or the many apparent input parameters. The schema's own 'discarded' fields partially mitigate this, but the description itself is still minimal.

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 baseline is met. The description's 'named IANA' wording only echoes the zone parameter's schema description and adds no new guidance about which of the nine parameters is relevant or how they interact.

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

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

The description clearly identifies the tool as returning the current time in a named IANA timezone, which separates it in intent from siblings like utc-time and iana-zones. It is specific about the resource though not framed as an explicit verb or direct contrast with siblings.

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

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

No guidance is given for when to use this tool versus alternatives such as utc-time or iana-zones. The only usage signal is implied by the phrase 'named IANA timezone,' but no when/when-not or alternative routing is stated.

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?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It fails to mention that the nine input parameters are ignored, that the tool is read-only, or what format the timestamp is returned in (e.g., ISO 8601, Unix epoch). The odd input schema with shape-checked and discarded fields is left unexplained, leaving important behavior invisible.

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, so it is structurally concise. However, its brevity is a symptom of under-specification rather than deliberately packed value. It omits essential details about expected behavior and parameters, so while it is short, it does not earn its place because it leaves critical gaps.

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 input parameters, no output schema, and no annotations. The description gives no context for what those parameters do, why they exist, whether they affect the output, or what the timestamp's representation is. Without any output schema, the description itself must explain the return value and any side effects, and it does not.

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 covers all 9 parameters with descriptions, so schema_description_coverage is 100% per the context signal, yielding a baseline of 3. The description itself adds nothing beyond the schema, but per the rules, with full coverage the description need not repeat the schema content. Thus a 3 is appropriate.

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

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

The description 'Current UTC timestamp' is a tautology of the tool name 'utc-time', adding only the adjective 'Current'. It lacks a verb phrase and does nothing to distinguish this tool from siblings such as 'timezone' or 'iana-zones'. An agent is left with no explicit statement of what is returned beyond a generic timestamp.

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 indication of when to use this tool, when not to use it, or any alternative. There is no mention of the sibling tools or expected context. An agent gets zero guidance on how to choose auto time and tool.

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

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

The description discloses one behavioral trait: the body is discarded after the check. However, it does not mention what the tool returns (e.g., boolean, success/error), whether there are side effects, or the safety profile. With no annotations available, the behavioral burden falls entirely on the description, and it only partially addresses it.

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

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

The description is two short sentences, with the core action immediately stated and the behavioral note about discarding placed right after. There is no filler or extraneous detail. It earns high marks for economy and clarity despite being thin.

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

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

With no required parameters, nine optional parameters, no output schema, and no annotations, the description leaves the agent without enough context. It fails to identify which parameter carries the JSON body, why the other eight exist, or what successful validation looks like. This is a substantial completeness gap for a multi-parameter tool.

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

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

The schema description coverage is 100%, and every parameter has an individual description, which already explains each parameter's meaning. The tool's description adds no extra semantic value beyond that. The schema's own description of 'json' ('JSON text to validate; discarded after the check') is what communicates the core input, so the baseline 3 is appropriate.

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

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

The description states a specific verb and resource: 'Check whether a body is valid JSON.' It is clear enough to distinguish this as a JSON validation tool by intention, but it does not explicitly differentiate itself from sibling validation tools like domain-shape or browser-url-ok. The word 'body' is slightly ambiguous but not 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?

There is no guidance on when to use validate-json versus its siblings, nor what input condition selects it. The description gives no usage context, no prerequisites, and no references to alternatives. An agent is left without direction on when this tool should be chosen.

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

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

The description discloses an important behavioral trait: a call to the external Open-Meteo service. However, with no annotations to fall back on, it does not explain that the action is read-only, what format or unit the temperature is returned in, what happens on API failure, or that the other optional schema parameters are ignored. The basic behavior is stated, but beyond that is thin.

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

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

The description is a single sentence with no filler or repetition, and the core idea is front-loaded. It is appropriately short for a tool with a rich schema, but it could earn its place better by adding one clause, such as what the caller receives.

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 annotations, and no output schema, this description provides only the high-level intent. It does not specify the output value, unit, whether the city must be internationally recognized, or how to handle failures—so an LLM cannot fully predict what will happen when the tool is invoked.

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

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

Schema description coverage is 100%, so the schema already documents all nine parameters individually, giving this a baseline of 3. The tool description itself adds little parameter meaning beyond naming a city, and it does not tell the agent to ignore the other eight parameters, but the schema-level descriptions are sufficient to avoid missing parameter documentation.

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?

"Current temperature for a city via Open-Meteo" clearly names a specific action and resource, so it is not a tautology. It does not explicitly distinguish itself from sibling tools like geo-hint or timezone, and the 9-parameter schema makes the intended resource less obvious, but the core purpose is clear.

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

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

The wording implies usage whenever the agent needs the current temperature for a city, but it provides no explicit when-to-use, when-not-to-use, or alternatives. There are no exclusions or conditions such as 'only for a single point-in-time query' or 'not for forecasts', so an agent must infer the boundaries.

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

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

With no annotations, the description carries the full burden. It does disclose that the HTTP body is discarded, which is useful, but it gives no indication of how the other 8 parameters are handled (e.g., whether they are ignored, trigger separate checks, or require network access). The one disclosed behavior only covers the 'url' param, leaving the rest 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 concise—two sentences with no filler or repetition. The key behavioral fact ('Body discarded') is front-loaded. However, it is so terse that it omits critical information, but for pure conciseness it earns a high mark.

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

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

Given 9 parameters, no output schema, and zero annotations, the description is far from complete. It covers only the URL case and says nothing about the remaining parameters, their expected inputs, or the output shape. An agent cannot reliably invoke this tool for non-URL use cases based on this 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?

Schema description coverage is 100% and each parameter has a meaningful description in the schema. The tool description itself adds no extra parametric meaning; it only mentions the URL attribute implicitly. Baseline 3 is appropriate: schema does the heavy lifting, but the description provides no added guidance for non-URL params.

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

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

The description states a specific verb and resource ('HTTP status and content type for a public URL') but is too narrow: the schema exposes 8 additional parameters (city, zone, json, etc.) with no mention in the description, so the tool's full scope is unclear. It also doesn't distinguish from siblings like fetch-status or browser-url-ok, which may have similar behavior.

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 vs alternatives. There is no mention of conditions for choosing it, what types of URLs it handles, or what to use instead. The presence of many sibling tools without any routing hints leaves the agent without selection criteria.

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

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

With no annotations, the description carries the full burden of explaining side effects and state changes. It only says a title is discarded after the call, but no title input exists in the schema, making that statement effectively meaningless. It does not disclose how the tool behaves with the provided ref, url, city, feed, host, json, path, zone, or query 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, but it is short at the expense of usability. It front-loads the wrong concept ('title') and includes a discard note that does not map to the actual input schema, so every sentence either misleads or fails to help 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?

The tool has nine optional parameters, no output schema, and no annotation safety context, yet the description explains none of these. It is impossible for an agent to infer which parameter to use, what the result means, or how calling this tool differs from calling adjacent 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?

The description adds no semantic value to the parameters; it never associates the 'Wikipedia title' concept with any of the nine schema properties. Although the schema has 100% description coverage, the schema descriptions are generic one-liners such as 'discarded after the shape check' and do not support the stated purpose of looking up a Wikipedia title.

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 'Check whether a Wikipedia title exists,' which names a clear verb and resource, but there is no parameter for a Wikipedia title in the input schema. The phrase 'Title discarded after the call' is misleading because no parameter is named 'title' and all nine properties are unrelated to Wikipedia titles.

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 its many siblings, such as browser-url-ok, file-path-ok, validate-json, or search-query-len. The description does not explain which of the nine unrelated parameters should be populated or in what combination.

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