Port 21

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

With no annotations provided, the description must disclose behavioral traits. It mentions 'Task text discarded' and 'Returns connection methods', but says nothing about side effects, cost implications (pay-per-call), or what happens to the parameters (many schema descriptions say 'discarded after', but the main description does not state that). The tool appears to be read-only, but that is not explicitly stated.

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

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

The description is very brief, two sentences, and leads with the core purpose. There is no extraneous text. However, the brevity comes at the cost of missing essential guidance, but for conciseness alone, 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?

The tool has 9 optional parameters, no annotations, and no output schema, yet the description provides almost no contextual completeness. It does not explain how to invoke the tool, what the 'connection methods' look like, or how the parameters map to the task. An agent would have no idea what to pass or what to expect back, making this seriously inadequate for a tool with such a broad parameter set.

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

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

While the input schema provides 100% parameter descriptions, the tool description adds no context on how these parameters relate to the stated purpose. The parameters (city, feed, host, json, path, zone, query, etc.) seem unrelated to 'finding a gateway' and appear to be validation inputs for other tools. The description does not bridge this gap, so an agent cannot infer which parameters are relevant for a given task.

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

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

The description states a specific action ('find a public pay-per-call tool gateway') and a resource type, but it is vague about how the tool actually accomplishes this. It lists example tasks (weather, search, scrape, voice) without mapping any of the 9 input parameters to those tasks, leaving the agent unsure of what to supply. The phrase 'Task text discarded' adds a constraint but does not clarify the core purpose.

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

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

The description gives no guidance on when to use this tool versus the many sibling tools (e.g., weather-hint, search-query-len). It does not mention alternatives or provide conditions for selection. The only contextual hint is the list of example tasks, but it does not explain how this index relates to the dedicated per-task tools.

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

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

With no annotations, the description bears the full burden of explaining side effects. It discloses that no browser is launched, but it does not mention whether a network request is made, whether any data is fetched or cached, what errors can occur, or whether the operation is read-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 short and front-loaded, and both sentences are relevant. However, it is too terse to be considered well-sized because it omits essential details about which input matters and what the check entails.

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 9 optional parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain the role of the unrelated parameters, what the tool returns, how the URL check is performed, or under what conditions it succeeds or fails.

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

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

Although the schema description coverage is 100%, the parameter descriptions are confusing and mostly irrelevant to the stated purpose. For example, 'url' is described as 'HTTPS URL to normalize or cite' rather than the URL to check, and fields like 'ref', 'city', 'feed', and 'query' are marked as 'discarded,' which actively misleads an agent about the tool's actual behavior.

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

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

The phrase 'Check whether a URL can be opened' states a broad action and object, but it does not specify which parameter is the URL, what 'opened' means, or how this differs from sibling tools like fetch-status, web-fetch, or playwright-url-ok. The purpose is too vague to guide an agent reliably.

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 explicit guidance about when to prefer this tool over alternatives. The only hint is 'No browser is launched,' which implicitly suggests a lightweight check, but it does not say when to use this versus other URL-related sibling tools.

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

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

No annotations are provided, so the description must fully disclose behavior. It says 'Expression discarded' but does not explain what happens to the provided parameters, whether the tool validates them, returns a result, or has side effects. The reference to arithmetic is inconsistent with the actual parameters, and no return format or side effects are described.

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

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

The description is short, but it is under-specified rather than concise. Two sentences, the first of which is inaccurate and the second ambiguous, fail to convey any useful information. Efficiency is irrelevant when the content is 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?

With 9 parameters and no output schema, the description provides almost no context. It does not explain the purpose of the parameters, the expected behavior, or the return value. An agent cannot correctly invoke this tool based on the description alone, especially given the mismatch between the description and schema.

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

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

The schema descriptions already cover 100% of parameters (e.g., 'Git ref name; discarded after the shape check'), so the baseline is 3. However, the tool description adds no meaning beyond the schema and actively introduces a misleading concept of arithmetic that is not reflected in any parameter, potentially confusing the agent.

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 'Evaluate a+b style arithmetic' but the input schema contains parameters like ref, url, city, feed, host, json, path, zone, and query – none of which represent an arithmetic expression. The stated purpose is misleading and does not match the actual tool function, which appears to be some kind of shape check or validation based on the parameter names.

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 its siblings such as domain-shape, file-path-ok, or normalize-url. There is no mention of conditions, exclusions, or alternatives, leaving the agent without any basis to select it.

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

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

The only behavioral note is that page content is not stored, offering minimal transparency. Other potential side effects, error behaviors, or data handling are not mentioned, and no annotations exist to fill the gap.

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

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

The description is extremely concise, consisting of a single sentence that states the core function and one caveat. It is efficient and well-structured.

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

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

Given the tool has nine optional parameters and no output schema, the description is severely incomplete. It fails to explain which parameter is required for the core function, how the other parameters affect behavior, or what output format to expect.

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

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

The description does not clarify any of the nine parameters. The schema descriptions are generic and seem unrelated to the stated purpose (e.g., 'ref' as a Git ref name), so the tool's actual inputs remain ambiguous.

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

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

The description clearly states the tool returns host, scheme, and HTTP status for a URL, which is a specific and actionable purpose. However, it does not explicitly identify which parameter is the URL, though 'url' is an obvious candidate.

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 lacks any comparison to sibling tools or contextual triggers for its use.

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 and parameter notes disclose that identifiers/inputs are not retained and some values are discarded after checks, which is useful privacy context. However, there is no mention of side effects, errors, return behavior, or required permissions, and no annotations are provided to fill these gaps.

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

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

The description is short and free of unnecessary words, and the parameter descriptions are compact. The structure is clean, though the brevity comes at the cost of substance.

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

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

There is no output schema, no example classification, and no explanation of the relationship between the input fields and the classification result. The tool is missing critical context for an agent to understand or 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?

Each parameter has a terse one-line hint, but these hints do not explain how the parameter affects classification or which combinations are valid. With all parameters optional and no required fields, the agent is left uncertain about what input shape is expected.

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' but never defines what classification means, what categories are produced, or how the tool's output is structured. It names an action and a resource but leaves the core purpose ambiguous.

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

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

There is no guidance about when to use this tool versus the many sibling tools. No conditions, prerequisites, or alternative selection criteria are mentioned, so an agent cannot decide when this tool is appropriate.

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

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

No annotations are provided, so the description carries the full burden. It discloses the exclusion of WHOIS/ownership data, but says nothing about the behavior for the other 8 parameters, the return format, or side effects. This is a minimal disclosure for a tool with such a broad parameter set.

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. It front-loads the core action and the key exclusion, making it easy to parse.

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

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

For a tool with 9 optional parameters, no annotations, and no output schema, this description is drastically incomplete. It does not explain why parameters like 'city' or 'feed' are relevant to splitting a hostname, nor what the tool returns. An agent cannot reliably invoke this tool correctly based on this description alone.

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

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

The input schema already describes all 9 parameters with specific details (e.g., 'discarded after the shape check'). The tool description adds no additional parameter information, so it stays at the baseline for high schema coverage.

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

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

The description states a specific verb ('Split') and resource ('hostname') and clarifies it excludes WHOIS/ownership data, which distinguishes it from sibling shape tools. However, the input schema contains 9 unrelated parameters (city, feed, json, etc.) that contradict the narrow hostname focus, creating confusion about the tool's true scope.

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

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

The description gives a negative constraint ('without WHOIS or ownership data') but does not name any alternative tools or conditions for when to use this tool vs others. With 28 siblings, this is insufficient 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?

The only behavioral detail is 'Path discarded,' which is minimal. With no annotations to cover side effects, the description leaves unclear whether the tool performs network access, validation, or simply parsing the URL string.

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

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

The description is very short and easy to read, but it omits critical information such as the output format or which parameters are meaningful. It is concise at the expense of usefulness.

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

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

Given the tool has 9 optional parameters and no output schema, the description is far too thin. An agent cannot determine expected return value, parameter relevance, or error conditions, making the tool effectively opaque.

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

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

Schema descriptions cover 100% of parameters, but most parameters (city, feed, host, json, query, etc.) are unrelated to a Figma URL parser and appear to be boilerplate. The descriptions do not clarify which parameters are actually relevant to this tool's purpose.

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

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

The description states a clear verb and resource ('Parse a Figma file URL') and notes the path is discarded, but it does not specify what output is produced (e.g., whether it returns a normalized URL, a validation result, or extracted components). It is not enough to distinguish it from sibling tools like domain-shape or normalize-url beyond the Figma-specific subject.

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 never mentions related tools or conditions for preferring this over normalize-url, domain-shape, or other sibling validators.

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 tool description says it counts HN stories, but every parameter description states the value is 'discarded after the shape check', implying the tool actually performs a validation or shape check rather than a count. This direct contradiction makes the true behavior opaque and 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 tool description is a single, concise sentence that delivers the core purpose without extraneous words. However, the parameter descriptions are lengthy and irrelevant, though they are part of the schema rather than the main description, so the main description itself is well-structured and brief.

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

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

The description is too brief to provide a complete understanding of the tool's behavior, especially given the contradictory parameter descriptions. It fails to explain why the parameters exist, what 'shape check' means, or how the count is obtained, leaving the tool's actual function ambiguous and 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?

All nine parameters are optional and their descriptions reference unrelated concepts (git ref, URL, city, feed, host, JSON, path, timezone, query) and explicitly note they are discarded. These parameters provide no meaningful input for counting HN stories and appear to be placeholder or generic fields, adding no semantic value.

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

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

The description clearly states the verb 'Count' and the resource 'current Hacker News front-page stories', making the intended purpose understandable. It is concise and specific enough to distinguish from generic fetch tools, though it does not explain the unusual 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?

The description provides no guidance on when to use this tool versus alternatives like web-fetch or fetch-status. With nine optional parameters all described as 'discarded', there is no indication of what input is expected or how the counting is performed, leaving the user without practical 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?

With no annotations and no additional description, the tool's side effects, read-only nature, or output behavior are not disclosed. The param descriptions mention values being 'discarded,' but this is inconsistent and unexplained.

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

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

The description is a single, short sentence with no filler. It is concise, though it sacrifices necessary detail for brevity.

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

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

Given the 9 optional parameters, no output schema, and no annotations, the description is far too sparse. It does not explain what the tool returns, how parameters are used, or why most are 'discarded.'

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 provides descriptions for all 9 parameters, so coverage is high and the baseline is 3. However, the tool description adds no extra meaning, and several param descriptions seem unrelated to timezone names.

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

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

The description states the tool deals with 'common IANA timezone names for clock calls,' but it lacks a clear verb or explicit function. It is unclear whether the tool returns a list, validates a name, or does something else entirely.

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 the many sibling tools, such as timezone, utc-time, or weather-hint. The phrase 'for clock calls' is too vague to inform 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 provided, the description carries the transparency burden. It states a read-only fetch of a public resource and restricts output to counts only, and several parameter descriptions explicitly note that values are 'discarded' or that there is 'no disk access'. It does not explicitly mention network side effects or caching, but the behavior is largely transparent.

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

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

The main description is one short sentence with no redundant wording, and the structure is clean. It would benefit from more detail, but it is concise and easy to parse.

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

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

Given nine optional parameters, no output schema, and no annotations, the minimal description leaves significant gaps. An agent cannot determine which parameters are relevant, whether any are required, or how 'group counts' are computed or returned.

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

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

All nine parameters have individual descriptions, but most are unrelated to robots.txt (e.g., city, json, zone, query) and the main description does not explain how they connect to the tool's purpose. The 'discarded' notes clarify that some inputs are ignored, but the intended use of url, host, and path remains ambiguous.

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

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

The description clearly specifies the action ('Fetch'), the target ('public robots.txt'), and the expected output ('group counts only'), which distinguishes it from broader tools like web-fetch or fetch-status. However, 'group counts' is not defined, and the abundance of unrelated optional parameters slightly muddies the intended purpose.

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

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

No guidance is given for when to use this tool over sibling tools such as web-fetch, fetch-status, normalize-url, or domain-shape. The description only states what the tool does, not when it should be preferred or when alternatives should be used instead.

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, but it only states that the body is discarded. It does not mention that most of the nine parameters are discarded after shape checks, any network behavior, or error conditions, and it conflicts with the schema's broad parameter set.

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, which is efficient. However, the brevity omits critical information about the tool's actual behavior across its many parameters, so it is not fully effective.

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, this description is grossly insufficient. It never explains what 'hint' means, what the tool returns beyond 'HTTP status,' or how to select among the parameters.

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

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

Schema description coverage is 100%, so a baseline of 3 applies, but the description actively misleads by implying only a URL is relevant while the schema accepts nine distinct inputs. It adds no clarification about which parameter yields the HTTP status or how the 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 states a specific verb and resource ('HTTP status for a public library docs URL'), but the input schema contains nine unrelated parameters (city, zone, json, path, query, etc.), making the stated purpose misleading. It does not distinguish this tool from siblings like fetch-status or web-fetch and fails to describe the actual scope of the 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?

No guidance is given on when to use this tool versus alternatives such as fetch-status, web-fetch, or normalize-url. The only contextual clue is 'public library docs URL,' but there are no explicit exclusions, prerequisites, or comparisons to sibling tools.

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

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

No annotations exist, so the description must disclose behavioral details. It mentions counting keys but omits error handling for invalid JSON, how non-JSON parameters are treated, or whether any side effects occur.

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, but this brevity sacrifices necessary detail and clarity, making it under-specified rather than effectively concise.

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

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

With nine parameters and no output schema, the description provides insufficient context about expected inputs, outputs, or edge cases, leaving the tool's behavior largely 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?

While the schema covers all parameters with descriptions, the tool description does not clarify which parameter is used or how the irrelevant parameters are ignored, adding no semantic value beyond the schema.

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

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

The description provides a verb ('Count') and a resource ('keys in a JSON object'), but it does not clarify which input parameter contains the JSON object, leaving the purpose ambiguous given the nine available 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 alternatives like validate-json or search-query-len, and no context for appropriate invocation scenarios is 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?

The description mentions that query and fragment are dropped, but it does not disclose side effects, permissions, network access, or persistence behavior. With no annotations provided, the description carries the burden and only partially explains 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 concise, using two short sentences with no filler or redundant phrasing. It directly states the operation and the transformation applied.

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

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

The description lacks detail about the output format, error behavior, and the role of the many optional parameters. Since there is no output schema, more context about the returned structure would be necessary for reliable use.

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

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

Each parameter has a schema description, but the tool description only addresses 'url' and 'query' indirectly. Parameters like 'ref', 'city', 'feed', 'json', 'zone', 'host', and 'path' are not connected to the stated purpose of URL normalization at the tool level.

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 origin, host, and path for a URL and that query and fragment are dropped. This gives a direct sense of the primary purpose, though the presence of many unrelated parameters adds some confusion.

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

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

The description provides no guidance on when to use this tool versus alternatives like fetch-status, web-fetch, or browser-url-ok. There is no mention of suitable use cases, edge cases, or when not to use it.

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

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

The description discloses one behavioral trait ('No browser is launched'), but omits that it performs shape checks on various inputs and discards them, as implied by parameter descriptions. With no annotations, the description carries the full burden and fails to explain these behaviors.

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

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

The description is a single concise sentence, but it is under-specified for a tool with 9 parameters, so it sacrifices completeness for brevity.

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

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

For a tool with 9 optional parameters and no output schema, the description is severely incomplete. It does not explain the tool's overall purpose beyond URL checking, nor does it clarify the role of the other parameters.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no parameter-specific information beyond the schema, so it does not improve semantics.

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

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

The description states a clear verb and resource ('Check whether a URL can be opened'), but it fails to mention the tool also validates many other input types (ref, city, feed, host, json, path, zone, query) as evidenced by the input schema. This makes the stated purpose incomplete and potentially misleading about the tool's full scope.

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

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

No guidance is provided on when to use this tool versus siblings like browser-url-ok or web-fetch. The description gives no context for 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, and the description does not disclose any behavioral aspects such as input handling, return format, side effects, or error conditions. Additionally, the description is completely unrelated to the input schema (which contains parameters like 'git ref', 'URL', 'city'), making the tool's behavior entirely opaque and even contradictory to its apparent purpose.

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

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

The description is very short and concise in length, but it contains no substantive information. Conciseness is not beneficial when the content is essentially meaningless or irrelevant to the tool's function, so it fails to provide even a minimal useful structure.

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

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

Given the tool has 9 parameters and no output schema, the description is grossly incomplete. It does not explain what the tool does with any of the parameters, what it returns, or any expected behavior. The single sentence leaves nearly every aspect of the tool's execution and context 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?

The input schema has 9 parameters, each with a description, but these descriptions reference unrelated domains (e.g., 'Git ref name', 'HTTPS URL', 'City name') that do not connect to the tool's stated purpose about port 21. The tool description does not clarify or add meaning to any parameter, so the parameter semantics are entirely ambiguous and misleading.

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

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

The description 'Whether 21 is a common TCP/UDP port' is a factual statement, not an action or a clear tool purpose. It does not state what the tool does (e.g., checks or verifies) and provides no context that distinguishes it from the many sibling tools, which appear to perform various URL, validation, and lookup functions.

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 alternative. The description does not mention any use cases, prerequisites, or comparisons with related tools, leaving the agent without any information about when this tool would be appropriate.

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

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

Without annotations, the description should disclose behavior itself, but it only says 'Prompt discarded' without explaining what happens to the nine input parameters, what the template contains, or whether there are 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 concise and the main verb phrase is front-loaded, but the brevity sacrifices important details and the second sentence is unclear.

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 a 9-parameter schema, no output schema, and no annotations, the description is far too incomplete to let an agent know what to expect, how to call the tool, or what the returned template 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?

Each parameter has a schema description, but several explicitly say 'discarded' and the descriptions appear unrelated to the tool's stated purpose, so they do not meaningfully clarify how parameters affect the result.

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

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

The description states the tool returns a three-step thinking template, but the meaning is vague and the second sentence 'Prompt discarded' introduces confusion without clarifying what prompt or how it relates to the tool's purpose.

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

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

There is no guidance on when to use this tool, what problem it solves, or how it compares with the many sibling 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, so the description carries the full burden of behavioral disclosure. It is a single line that reveals nothing about side effects, that non-zone parameters are discarded, or the nature of the operation, leaving the agent to assume it is a safe read.

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, waste-free sentence that is fully front-loaded. It is appropriately brief, though the brevity edges toward under-specification given the tool's 9-parameter surface.

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

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

With 9 optional parameters, no annotations, and no output schema, the description says almost nothing about how to invoke the tool correctly — it does not indicate that 'zone' is the operative parameter or that the rest are ignored. The rich schema compensates partially, but the description alone is thin for 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 description coverage is 100%, so the baseline is 3. The schema richly documents each of the 9 parameters, including which are discarded, and the description adds no parameter detail beyond the schema's own notes.

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-resource pair ('Current time in a named IANA timezone'), clearly identifying the tool as a time lookup. It is implicitly distinct from sibling 'utc-time' (which is UTC-specific), though it does not explicitly name the distinction.

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 like 'utc-time' or 'iana-zones'. With siblings covering UTC and zone listing, an agent gets no help choosing among them beyond inferring from the name.

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

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

The description discloses no behavioral traits—no statement about read-only nature, network calls, or side effects. Since there are no annotations, the description carries the full burden, and it fails. Moreover, the parameter descriptions are misleading (e.g., 'ref' is described as 'Git ref name; discarded after the shape check'), suggesting the tool performs arbitrary validation checks unrelated to weather, further obscuring actual behavior.

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

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

The description itself is concise—one clear sentence. However, the overall structure is poor because the input schema is cluttered with 9 parameters, most of which are irrelevant to the tool's purpose. The description does not help organize or prioritize these parameters, so while the text is brief, the structure as a whole is confusing.

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 optional parameters and no output schema, the description is severely incomplete. It does not explain which parameters are essential, how they are used, or what the response looks like. The agent is left without any guidance on how to invoke the tool correctly, especially since most parameters appear to be irrelevant carryovers from other 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 schema has 100% coverage, but the descriptions are largely irrelevant and copied from other tools (e.g., 'url' as 'HTTPS URL to normalize or cite', 'json' as 'JSON text to validate'). Only 'city' and 'zone' have any plausible relevance, but even these are vague ('City name for a public weather hint; discarded after the call'). The description adds no clarification about which parameters are actually used or how they affect the weather query, providing minimal semantic value and actively misleading the agent.

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

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

The description clearly states the tool's function: obtaining the current temperature for a city via Open-Meteo. It uses a specific verb ('Current temperature') and identifies the resource ('a city via Open-Meteo'). However, it does not specify the output format or distinguish it from sibling tools, which are mostly about URL checks, math, and other utilities, so it loses a point for not being more explicit about its scope.

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

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

The description provides no guidance on when to use this tool versus alternatives. There is no mention of scenarios where weather data is needed, nor any comparison with sibling tools. The only hint is the tool name 'weather-hint,' but the description itself offers no usage context.

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

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

The description notes that the body is discarded, but with no annotations it does not disclose external network behavior, error cases, redirects, rate limits, or side effects.

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

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

The description is a concise two-sentence statement with no wasted words, though it lacks any structured elaboration.

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

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

Given the nine-parameter schema and overlapping sibling tools, the description omits essential context such as which parameter is the primary input, what the response looks like, and how failures are reported.

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

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

Although every parameter has a description, most descriptions are irrelevant to fetching a URL (e.g., 'Git ref name', 'City name', 'IANA timezone name'), and the url parameter is described as 'normalize or cite' rather than fetch; all parameters are optional, so the required input is unclear.

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

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

The description states a specific action and resource ('HTTP status and content type for a public URL'), but the input schema includes many unrelated optional fields, leaving the actual fetch target ambiguous.

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

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

No guidance is given about when to prefer this tool over sibling tools such as fetch-status, browser-url-ok, or normalize-url; the only implicit use case is needing status/content type and not the body.

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

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

With no annotations provided, the description carries the full burden. It mentions 'Title discarded after the call,' implying a stateless, read-only check, but it does not disclose the result format, error behavior, or any side effects. This minimal disclosure is insufficient 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 brief, consisting of two sentences with no redundancy. However, this brevity borders on under-specification; it omits critical invocation details. It is concise but not effectively structured for agent comprehension.

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, this description is grossly incomplete. The agent has no idea which parameter to use, what the return value represents, or how to interpret success/failure. The description fails to provide the necessary context for correct invocation.

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

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

Although schema coverage is 100%, the parameter descriptions are generic and mismatched (e.g., 'query' is 'Search text' and 'path' is 'File path to check'), with no indication of which parameter holds the Wikipedia title. The description adds no clarity about parameter usage, so it fails to compensate for the schema's irrelevance.

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

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

The description states a specific verb and resource: 'Check whether a Wikipedia title exists.' This clearly distinguishes it from sibling tools that handle URLs, domains, or other entities. However, it does not explicitly differentiate from potential overlapping tools or name alternatives, so it falls 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 guidance on when to use this tool versus siblings, nor any mention of prerequisites or context. The description provides no exclusions or alternative routing, leaving the agent to infer usage from the name alone.

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