E.164 shape, number discarded

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It usefully adds 'Page content is not stored,' which clarifies a key side effect (no content persistence) and sets expectations about privacy. However, it doesn't disclose other behaviors like whether it fetches the URL, network dependencies, or what happens on invalid URLs. The added note is helpful but incomplete.

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 that is front-loaded with the main purpose, followed by an important clarifying clause about content storage. It is efficient and easy to parse, though it could be slightly more structured to mention the multi-purpose nature of the tool (URL, host, JSON, zone).

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 no annotations and no output schema, the description is short and leaves out several operational details, such as whether a network request is made, what the returned status range looks like, and how the `host`, `json`, and `zone` parameters are validated. The 'Page content is not stored' note adds some user-facing context, but an agent might still be uncertain about invocation semantics for most 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 the schema already documents all four parameters. The description only explains the URL-related purpose and does not add meaning for `host`, `json`, or `zone` parameters. It does add a behavioral note about JSON being 'discarded after the check,' which aligns with the schema but doesn't significantly enhance parameter understanding. 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 action (`Return host, scheme, and HTTP status for a URL`) and names the resource (a URL), distinguishing it from typical citation tools that might store or format a full citation. It is clear about what the tool does, though it doesn't explicitly differentiate from the wide range of sibling tools shown in context.

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

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

The description offers no explicit guidance on when to use this tool versus alternatives or when it is not appropriate. The sibling list shows many similarly named tools, but the description provides no routing context, such as 'use for simple URL validation or normalization' or 'use for time zone validation instead of ...'.

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 present, the description carries the full burden of behavioral disclosure. It reveals a privacy-relevant behavior (identifiers are not retained) but remains silent on what 'classified' means, how the four parameters (url, host, json, zone) are consumed, and what the tool returns. This is a meaningful gap for a tool that appears to perform some kind of request analysis.

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

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

The description is short and front-loaded, with no wasted sentences. The two statements are efficient. However, the brevity comes at the cost of clarity, and the phrase 'Show how this request is classified' is vague enough that conciseness does not fully serve 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 no output schema and no annotations, so the description is the sole source of contextual information. It fails to explain what 'classified' produces, how an agent should interpret the response, or when this tool is relevant relative to its siblings. For a tool with four heterogeneous parameters, this is incomplete.

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

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

Schema description coverage is 100%, so the baseline is 3; each parameter (url, host, json, zone) already has a clear description in the schema. The tool description does not add parameter-specific meaning, such as how the parameters relate to classification or whether they are alternatives or jointly required. It neither compensates for a schema gap nor adds value beyond it.

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

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

The description 'Show how this request is classified' states a verb but does not specify what classification means, what kind of request, or what output the agent should expect. It is not a clear verb+resource statement and does little to distinguish the tool from its siblings, which already cover citation, URL normalization, validation, and timezone conversion.

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 explicit guidance on when to use this tool versus its siblings. The privacy note ('No identifiers are retained') is useful but does not help an agent choose between compatibility, citation, normalize-url, validate-json, and similar tools. No exclusions, prerequisites, or alternative conditions are mentioned.

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

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

No annotations are provided, so the description must fully disclose behavior. It reveals the core pure transformation but says nothing about side effects, permissions, return values, or edge cases. The schema's json parameter note ('discarded after the check') hints at a different behavior than the description's split operation, creating confusion rather than transparency.

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

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

The description is a single front-loaded sentence with no filler; every word earns its place. However, for a tool with four parameters and no annotations, this brevity borders on under-specification, so it does not quite reach a 5.

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

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

With no annotations and no output schema, the description must carry the full invocation context. It explains only the hostname-splitting operation, leaves url/json/zone unintegrated, and says nothing about return format. An agent cannot confidently determine how to invoke the tool with the described purpose and the given 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 parameter-level meaning beyond the schema: it only indirectly maps to the host parameter and never explains how url, json, or zone participate in the described hostname-splitting task. It does not add value, but it also does not misinform by itself.

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 ('Split a hostname into labels') and explicitly carves out a non-goal ('without WHOIS or ownership data'), which distinguishes it from enrichment tools. However, the tool's schema includes url, json, and zone parameters that do not obviously relate to hostname splitting, so the description alone leaves some ambiguity 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 phrase 'without WHOIS or ownership data' provides an implicit when-to-use signal: choose this when you only need label splitting and not ownership enrichment. It does not name alternative tools or give explicit exclusions, and it gives no guidance on when to use the url, json, or zone parameters, so usage direction remains mostly implied.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It only states the content is 'common IANA timezone names' without saying whether the tool returns them, filters by zone, or ignores the url/host/json parameters. There is no mention of return shape, side effects, or failure 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 short but underspecified rather than concise; it omits the verb and actionable information while including only a vague 'for clock calls' hint. A one-sentence definition with a verb would fit the same length and be far more useful.

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

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

With 4 optional parameters, no output schema, no annotations, and sibling tools present, the description is severely incomplete. An agent cannot determine what the tool returns, how parameters like url/host/json are used, or when to call it.

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 semantic connection between the parameters and the tool's purpose—especially why url, host, and json appear in a timezone tool—but the schema already documents each parameter adequately.

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'—with no verb indicating what the tool does. It mostly restates the tool name (iana-zones) and adds a vague context hint, so it does not clearly distinguish the tool from siblings or state its action.

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

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

The only usage signal is 'for clock calls,' which implies a context but does not explain when to choose this tool over alternatives like validate or normalize. No exclusions, prerequisites, or alternative tool guidance 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?

With no annotations at all, the description carries the full burden of behavioral disclosure. It states the output is 'group counts only' but does not disclose behaviors like whether the fetch is idempotent, error handling on inaccessible robots.txt, rate limits, or caching behavior. 'Group counts only' is a useful constraint, but the description omits important behavioral context for an agent invoking an external network fetch.

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 concise sentence with zero waste. It front-loads the action (Fetch) and the constraint (public robots.txt, group counts only). Every word earns its place.

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

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

The tool is a network fetch with no annotations, no output schema, and four parameters that don't obviously map to the stated purpose. A description this short cannot fully explain how url, host, json, and zone relate to fetching a robots.txt, nor what 'group counts only' means in practice. There is no mention of error behavior, timeouts, or return format. For a tool performing an external fetch with zero structured safety annotations, more context is needed.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters: url, host, json, zone. However, these parameters are semantically odd for a robots.txt fetch — url is described as 'HTTPS URL to normalize or cite', json is 'JSON text to validate', and zone is 'IANA timezone name'. The description adds no parameter-specific detail, leaving it unclear how these relate to fetching robots.txt. The baseline of 3 applies due to full coverage, but the mismatch between the schema parameters and the tool purpose is a genuine gap the description could have addressed.

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: fetch a public robots.txt and return group counts only. This clearly identifies the core purpose, but it does not explicitly distinguish it from sibling tools beyond the inherent uniqueness of the operation. While 'group counts only' adds specificity, the description doesn't mention alternative tools or scenarios.

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

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

The description implies usage by stating 'Fetch a public robots.txt', but provides no explicit guidance on when to use this versus alternatives. It doesn't mention prerequisites like URL normalization or cite behavior. No exclusions or alternative tools are named, leaving the agent to infer when this is the right 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?

With no annotations provided, the description carries the full burden. It does disclose the core behavior: returning origin, host, and path, and dropping query/fragment. However, it does not clarify how the other schema parameters (json, zone, host) affect behavior, leaving ambiguity about what the tool actually does with them.

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

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

The description is only two sentences and contains no filler. It is front-loaded with the core purpose and includes an informative detail about dropped components. It is appropriately concise, though it sacrifices 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?

The description is incomplete for a tool with four unrelated-looking parameters and no output schema. It fails to explain why 'json', 'zone', and 'host' are accepted, and it does not describe the return structure. An agent cannot confidently invoke this tool correctly for anything beyond the basic URL case.

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 some meaning to the 'url' parameter by explaining the output and what is discarded, but it provides no insight into the 'json', 'zone', or 'host' parameters, creating a disconnect between the description and the full parameter set.

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: 'Return origin, host, and path for a URL. Query and fragment are dropped.' This is specific about the operation and output, and it distinguishes the tool from the sibling tools listed, which all have different purposes.

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

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

There is no guidance on when to use this tool versus alternatives. The description does not mention any conditions, exclusions, or related tools, so an agent has no context for selecting it over other options.

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

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

With no annotations, the description must disclose side effects and I/O behavior, but it only says the number is discarded. It does not say whether the tool performs network calls, returns a boolean, throws on invalid shape, or requires authentication, and 'discarded' is ambiguous about whether the result is a pass/fail verdict or removes the number from input.

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 brevity crosses into under-specification. It is a fragment rather than an actionable sentence, and it sacrifices necessary operational meaning for compactness.

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 four optional parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain the expected output, the relationship between the parameters and the E.164 check, or the conditions for successful 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 description never maps its E.164 'number' to any parameter. The schema exposes url, host, json, and zone, none of which is obviously a phone number, so the agent cannot tell what to pass. The phrase 'number discarded' adds confusion instead of clarifying which parameter carries the value to check.

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

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

The description is a noun phrase that restates the tool name ('E.164 shape') with one additional fact ('number discarded'). It never states an operation such as validates, normalizes, or extracts, so an agent cannot tell whether this is a check, a transform, or a filter. It also does not distinguish the tool from sibling domain-shape.

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

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

No guidance is given about when to invoke this tool or why it should be preferred over siblings like validate-json, domain-shape, or normalize-url. There are no exclusion conditions or alternative routing hints, leaving the agent to guess based on the name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it fails. It does not state whether the tool validates input, returns status codes, mutates anything, or what side effects occur. The parameters suggest some input-processing behavior, but the description gives no hint of 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 only six words, which is under-specification rather than effective conciseness. It lacks substance and does not earn its place because it conveys almost no actionable information to an agent.

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

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

For a tool with four parameters, no output schema, and no annotations, this description is severely incomplete. An agent cannot determine what the tool does, what inputs are expected, what it returns, or when to invoke it, making the definition nearly useless.

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

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

Schema description coverage is 100%, so the input schema already documents all four parameters. The description adds no meaning beyond the schema and does not explain how each parameter relates to the catalog, but baseline 3 applies because the schema covers the parameters adequately.

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

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

The description 'Short catalog of common HTTP status codes' merely restates the tool name 'status-catalog' without specifying any action the tool performs. It does not explain how the four input parameters (url, host, json, zone) relate to cataloging HTTP status codes, nor does it distinguish this tool from siblings like citation or compatibility.

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

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

No guidance is provided about when to use this tool versus its siblings. The description gives no context, prerequisites, or exclusion criteria, leaving the agent to infer the tool's purpose from the unhelpful 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?

No annotations are provided, so the description carries the full burden. It states the operation is a time lookup, implying read-only behavior, but it does not disclose the return format (e.g., ISO 8601 vs. local time), error behavior for invalid zone names, or whether the time is derived from the system clock or a data source. These are meaningful gaps for a tool with zero annotation coverage.

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 an 8-word single sentence, front-loaded with the core purpose and free of filler. It earns a 4, not a 5, because the schema mismatch is significant enough that a slightly longer description mentioning the relevant parameter would have been more valuable than extreme 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 no annotations, no output schema, and a schema polluted with three unrelated parameters, the description is insufficient. An agent cannot determine the return format, error handling, or which parameters are valid to pass without external knowledge. The one-liner identifies the tool's purpose but leaves the invocation contract dangerously underspecified.

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%, which sets a baseline of 3, but the schema contains four parameters where url, host, and json are clearly unrelated to time (descriptions reference 'normalize or cite', 'Public hostname', and 'JSON text to validate'). The description says 'named IANA timezone,' which aligns only with the zone parameter, but it does not warn the agent that the other three parameters are irrelevant, creating real confusion risk for tool invocation.

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 time in a named IANA timezone' clearly identifies the action (return current time) and the resource (a named IANA timezone). It is distinct from every sibling tool name (citation, compatibility, normalize, inspect, validate), none of which suggest time-related functionality. The verb is implied rather than explicit ('get'), and 'named' adds a slight scope qualifier, so it falls just 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?

No guidance is given on when to use this tool versus alternatives, no exclusions, and no conditions are stated. The description provides no routing information beyond the tool's inherent purpose, leaving the agent to infer suitability from the name and one-liner alone.

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

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

With no annotations, the description carries the full behavioral burden. It does not disclose what happens when the supplied parameters are present (are they ignored?), does not mention the output format (ISO string, epoch seconds, etc.), and gives no side-effect or safety information. The mismatch between the description and the input schema is a significant 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 extremely short and front-loaded, with no wasted words. It earns its place by stating the core purpose, but its brevity comes at the cost of missing necessary context about parameters and output format.

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 simple time tool, the description might suffice, but the presence of four irrelevant-looking optional parameters and a timezone sibling creates ambiguity. The description does not explain return format, whether inputs are ignored, or how this differs from 'timezone'. With no output schema to clarify the return value, this is incomplete.

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

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

Schema description coverage is 100%, so the baseline is 3. Each of the four parameters has a reasonable schema description. However, the tool description adds zero semantic link between these parameters and the UTC timestamp output, so an agent cannot infer how or whether they 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 'Current UTC timestamp.' states the output clearly but says nothing about how the four completely unrelated input parameters (url, host, json, zone) relate to that purpose. An agent cannot tell whether this is a simple clock, a timezone conversion tool, or a multi-mode utility. It also does not distinguish itself 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?

No guidance is given on when to use this tool versus alternatives. Since the sibling list includes 'timezone' and 'compatibility', an agent has no way to decide between them. The only implied usage is 'when you need current UTC time', but there is no explicit context or exclusions.

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

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

With no annotations provided, the description carries the full burden. It does add one useful behavioral detail: 'The body is discarded,' disclosing that no persistent state is kept. However, it does not disclose the return behavior (success/error, boolean vs details), whether any network call is made (the url parameter hints at this), or any side effects beyond discarding. It is partially transparent but not complete.

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

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

Two short sentences with zero filler. The core purpose is front-loaded, and the behavioral note about discarding is placed compactly at the end. Every word earns its place.

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

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

The tool is simple, but there is no output schema and no annotations, so the description must explain what the agent can expect back from a validation call — it does not. It also never clarifies what 'body' refers to relative to the schema's four parameters, and the presence of unrelated params (url, host, zone) could mislead an agent. The discarding behavior is noted, but the outcome and invocation focus are left ambiguous.

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

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

Schema description coverage is 100%, so the schema already documents each parameter individually. The description adds no parameter meaning beyond the schema; the only added phrase ('The body is discarded') is also present in the json param description. The description does not clarify which of the four params ('url', 'host', 'json', 'zone') is relevant, which is a missed opportunity given several unrelated sibling params appear 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 description states a specific verb and resource: 'Check whether a body is valid JSON.' This clearly distinguishes the tool from siblings like normalize-url or timezone, which deal with other data types. However, the word 'body' is ambiguous — it could mean the json parameter or an HTTP response body — so it is clear but not perfectly precise.

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 alternatives, and no exclusion criteria. Its usage is implied by the name and purpose ('validate JSON'), but it never explicitly says 'use this when you need to check if a JSON string is valid' or mentions when not to use it. Sibling tools are not referenced.

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