Base64 encode, input discarded

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

No annotations are present, so the description carries the full behavioral burden. It only discloses that input is discarded, but it doesn't describe return values, side effects, or which parameter actually gets encoded. That is a significant gap for a tool with no structured annotation support.

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, front-loaded with the primary action, and contains no filler. It is concise, though fragmented; the structural efficiency is good even if the content is under-specified.

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 four optional parameters, no output schema, no annotations, and a one-line description, the definition is not complete enough for reliable invocation. It fails to explain which parameter is the Base64 input, what the tool returns, and how it differs from the sibling tools around URLs, JSON, and timezones.

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's descriptions cover all four parameters, but they describe URL, host, JSON, and timezone semantics, none of which clearly relate to Base64 encoding. The description adds no mapping between a schema property and the 'input' it claims to encode, so an agent cannot confidently choose what to pass.

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 'Base64 encode,' which names an operation, but does not specify what input is encoded or how that relates to the schema's url/host/json/zone parameters. The phrase 'input discarded' muddles whether any input is actually processed, leaving the tool's true 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 on when to use this tool or when to prefer one of the siblings. It does not mention alternatives such as normalize-url or validate-json, and it gives no exclusion criteria or context that would help an agent route to 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?

There are no annotations, so the description carries the full burden. It does disclose one meaningful behavior: 'Page content is not stored.' However, it does not explain network behavior, rate limits, or how json/zone inputs fit into the operation.

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

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

Two sentences, front-loaded, with no filler. It is concise and readable, though it under-specifies the broader tool surface; that gap is better attributed to completeness rather than 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?

With four optional parameters, no annotations, and no output schema, the description is too thin. It covers only the URL case, leaves json/zone/host unexplained, and gives no output shape or usage context.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description adds little beyond a URL focus and does not reconcile 'host', 'json', or 'zone' with that focus, but the baseline of 3 applies.

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

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

Description uses a specific verb and resource: 'Return host, scheme, and HTTP status for a URL.' This makes the primary function clear. It does not explicitly distinguish from siblings like normalize-url or inspect-robots, and the schema's json/zone parameters fit awkwardly with the URL-only description.

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

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

No guidance is given about when to use this tool instead of related siblings such as normalize-url, validate-json, or status-catalog. It also does not explain which of the four optional parameters should be supplied for which task.

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

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

No annotations are provided, and the description does carry some behavioral burden. 'No identifiers are retained' is a meaningful statement about data handling, and the json parameter already notes it is discarded after the check. However, the description does not disclose whether the tool makes network requests, whether it is read-only, what side effects occur, or what the response contains.

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

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

The description is two short sentences with no filler. The core action comes first and the privacy note is a useful addition. Every sentence earns its place.

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

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

For a tool with four optional parameters, no output schema, and no annotations, the description is incomplete. It does not state what the classification result looks like, what 'compatibility' means, whether inputs are validated individually or together, or what the agent should do with the returned classification. The privacy note is helpful but does not make the tool actionable.

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 all four parameters already have descriptions. The tool description does not add param-specific meaning beyond the schema; 'No identifiers are retained' applies broadly but does not clarify how url, host, json, or zone are used in the classification. 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 says the tool shows how a request is classified, which is a verb plus a result, but it never explains what 'classified' means, what classifications exist, or what output to expect. It is vague rather than a tautology, so it is not a 1 or 2, but it does not clearly distinguish itself from siblings like validate-json or normalize-url.

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

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

There is no guidance on when to use this tool instead of the many sibling validators and formatters. The privacy note 'No identifiers are retained' implies a possible use case, but the description does not say 'use this when you need a privacy-preserving classification' or mention any alternatives.

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

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

No annotations are provided, so the description carries the full burden. It discloses only that the tool does not return WHOIS/ownership data; it says nothing about network calls, data retention, error behavior, or what happens with the unrelated optional params. This is minimal behavioral disclosure.

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

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

Single sentence, front-loaded with the action and no filler. Every clause earns its place, and the negative scope is useful context.

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

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

Given zero required parameters, no output schema, and no annotations, the description should clarify invocation and expected return. It only says split a hostname; it doesn't state what labels look like or which param to pass. The tool is too underspecified for an agent to call confidently.

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

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

Schema descriptions cover 100% of parameters, so the baseline is 3, but the description adds no link between 'hostname' and the four optional inputs (url, host, json, zone). It never says which parameter to provide, whether multiple parameters are allowed, or what happens when none are provided, so the high schema coverage does not resolve the ambiguity.

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

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

States a specific action ('Split a hostname into labels') and adds a scope exclusion ('without WHOIS or ownership data'). It is clear about the core operation, though it does not name an alternative sibling and the schema's extra params create some ambiguity.

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 about when to choose domain-shape over siblings such as normalize-url, validate-json, or iana-zones. The only hint is the negative scope ('without WHOIS or ownership data'), which is not enough to route an agent correctly.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It only states the content type (common names), not what the tool returns, whether it is read-only, or any edge cases; for a reference lookup this is a notable 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 a single compact phrase with no redundant words, and the key content 'IANA timezone names' is front-loaded. It lacks a main verb, which slightly weakens the structure, but it is not padded.

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

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

With no output schema and no annotations, the description should explain what the tool returns and how to invoke it; it does neither. The unrelated optional parameters and the lack of clarification about their relevance leave the agent without enough context to call the tool correctly.

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

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

Schema description coverage is 100%, so each parameter (url, host, json, zone) is already documented by the schema. The description adds no extra parameter-level meaning and does not clarify why url, host, and json appear relevant to a timezone-name tool, but the high schema coverage keeps this at baseline.

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

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

The description identifies the resource (common IANA timezone names) and the intended use (clock calls), making it clear this is a reference list rather than a conversion or validation tool. It lacks an explicit verb like 'returns' or 'lists' and does not differentiate from sibling tools such as timezone or utc-time, so it stops short of a 5.

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

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

'For clock calls' implies the tool should be used when supplying timezone names to clock-related operations, but there is no explicit when-to-use or when-not-to-use guidance. It does not name alternatives such as timezone or utc-time, leaving the routing decision to inference.

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

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

With no annotations, the description carries the burden of disclosure. It signals that the fetch is public and read-only and that only group counts are returned, which is useful behavioral context. It does not address errors, missing robots.txt files, or response format, so transparency is partial.

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

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

One short, focused sentence with no filler. The action, target, and output limitation are stated clearly and up front, making the description efficient 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?

The tool has four parameters, none required, and no output schema, but the description does not explain which parameters are relevant or what the returned group counts look like. The mismatch between the robots.txt purpose and the generic schema fields leaves an agent uncertain about how to invoke this tool correctly.

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

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

Schema description coverage is 100%, so the baseline is 3 even though the tool description adds no parameter-specific detail. The schema's property descriptions are generic and not tailored to robots.txt, so the description does not clarify how url, host, json, or zone relate to the 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 names a specific action ('Fetch'), a concrete resource ('robots.txt'), and an explicit output ('group counts only'), making it distinct from sibling tools like normalize-url or validate-json. An agent can tell exactly what this tool does from the first sentence.

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 the use case—fetching a public robots.txt and getting group counts—so an agent can infer when it is relevant. However, it never states when not to use this tool or mentions alternatives among the siblings.

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

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

With no annotations provided, the description carries the burden of disclosing behavior. It does reveal one meaningful behavior ('Query and fragment are dropped'), which helps an agent understand result transformation. However, it does not explain output shape, behavior on invalid URLs, or side effects, so transparency is partial.

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

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

Two short sentences with no filler. The primary action is front-loaded, and the extra behavioral detail ('Query and fragment are dropped') is placed concisely 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 has no annotations and no output schema, so the description must compensate. It states the basic result but leaves out the output structure, error behavior, and how the unrelated-looking parameters (json, zone, host) fit in. This is under-specified for a tool with four optional 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?

Although the schema has 100% description coverage, the description does not clarify how the url, host, json, and zone parameters relate to the described behavior. In fact, 'host' appears as a return value in the description while also being a parameter name, which could confuse an agent. The description adds no useful parameter semantics 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 uses a specific verb ('Return') and names the resource ('origin, host, and path for a URL'), and even adds a scoping detail ('Query and fragment are dropped'). It communicates the core purpose, though it does not explicitly differentiate itself from sibling tools like validate-json or utc-time.

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

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

No guidance is given about when to use this tool versus alternatives. There is no mention of preconditions, exclusions, or sibling tools. An agent must infer usage solely from the short functional statement.

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. 'Short catalog' only implies a passive reference read; it does not state whether the supplied url, host, json, or zone values are used, ignored, or discarded, nor what the response contains. The description is not contradictory, but it is behaviorally thin.

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

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

The description is short and contains no filler, which is a point in its favor. But it is so underspecified that it reads more like a label than a functional definition, and the brevity comes at the cost of missing operation and parameter guidance.

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

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

Given no output schema, no annotations, four optional parameters, and a schema that appears mismatched with the description, this is not enough for an agent to invoke the tool confidently. It does not explain how to use the inputs, what the output looks like, or whether the parameters are actually meaningful.

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

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

The schema has 100% description coverage, so the baseline is 3 even without parameter details in the description. Each parameter has its own description. However, the description adds nothing to explain why a URL, hostname, JSON text, or timezone would be relevant to a catalog of HTTP status codes.

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 essentially a noun-phrase restatement of the tool name: a catalog of status codes. It never states an operation such as 'returns', 'lists', or 'looks up', and it fails to connect the four unrelated input properties to the stated purpose. It identifies a domain but not what an agent should expect when invoking 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?

There is no guidance on when to use this tool versus any of the siblings. No alternatives, exclusions, or context are provided, so an agent cannot determine why status-catalog would be preferred over tools like validate-json, normalize-url, or iana-zones.

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

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

No annotations are provided, so the description must carry the full behavioral burden. It only says 'current time in a named IANA timezone' and does not disclose output format, invalid-zone behavior, or whether the zone parameter is the only relevant input. This is a thin behavioral contract.

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 scannable phrase with no filler and front-loads the key qualifier 'IANA timezone.' It is appropriately short for a simple read-style tool, though the fragment style and lack of an example keep it from being 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 four optional parameters, no output schema, and no annotations, this description is incomplete. An agent cannot confidently tell which parameter to populate, what the response format will be, or how this tool operationally differs from utc-time and iana-zones.

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 covers 100% of parameters, so the baseline is 3. The description adds only that the timezone is IANA, which maps to the zone parameter, but it does not add examples or clarify why url, host, and json are also present as optional fields.

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 names the resource ('current time') and scope ('named IANA timezone'), which distinguishes it from siblings like utc-time and iana-zones. It lacks an explicit verb and the schema's unrelated url/host/json parameters add ambiguity, so it is not 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 about when to use this tool versus siblings such as utc-time or iana-zones, and no mention of what inputs are needed in practice. The only usage context comes from the description's purpose statement, not from explicit selection guidance.

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

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

With no annotations, the description carries the full burden, but it only implies a read-only, side-effect-free call without disclosing what happens if only a url, host, or zone parameter is provided. The most important behavioral fact — that the tool seems to accept unrelated parameters despite being a simple timestamp read — is left entirely 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 undeniably short, but under-specification is not conciseness. A four-word phrase cannot cover the behavior of a tool whose schema exposes four parameters, so brevity here comes at the expense of necessary content.

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

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

Given a 4-parameter schema, no output schema, and no annotations, a four-word description is completely inadequate. There is no explanation of which parameters apply, why they exist on a UTC-time tool, or what the return value looks like, leaving an agent unable to call the tool correctly with confidence.

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

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

Schema description coverage is 100%, so the baseline is 3 even though the description adds no parameter semantics. However, the description actually undermines the schema: it suggests the tool takes no meaningful input, while the schema lists four well-documented optional parameters with no explanation of their relevance.

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

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

"Current UTC timestamp" is essentially a tautology of the tool name utc-time, restating the name rather than adding a verb, resource, or differentiation from the timezone sibling. It does communicate that the tool reports the current UTC time, but without a verb phrase or scope it reads as a label rather than an explanation.

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 about when to call this tool versus the timezone sibling, nor any context about how it behaves with the four optional parameters. There is no misleading guidance, just an absence of any usage direction.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It usefully states that the body is discarded, implying no retention or persistent side effect. However, it does not describe the return value, error behavior, or whether the unrelated `url`, `host`, and `zone` parameters play any role, so coverage is only partial.

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

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

Two short sentences with no filler; the core action is front-loaded. The second sentence slightly repeats the `discarded after the check` detail already present in the parameter schema, so it is not perfectly non-redundant, but it remains concise and readable.

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 an agent: there is no output schema and no explanation of what the tool returns, no statement that the JSON text should be passed via the `json` parameter, and no clarification of why the schema exposes unrelated properties like `url`, `host`, and `zone`. This leaves too much room for incorrect invocation.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds no real parameter semantics beyond the schema, and the word 'body' remains ambiguous relative to the `json` property. It neither improves nor contradicts the schema, so the baseline stands.

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 object: 'Check whether a body is valid JSON.' This clearly conveys that the tool validates JSON. However, the term 'body' is not explicitly mapped to the `json` parameter, and there is no contrast with sibling tools, so it is clear but not maximally 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?

There is no guidance on when to use this tool rather than a sibling, nor any mention of prerequisites or expected input form. An agent must infer the usage context solely from the tool name and the `json` parameter description.

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