Botcard

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

Annotations already declare readOnly, idempotent, openWorld=false, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: no network fetch occurs, output is one allow/disallow row per token with the vendor stance, and RFC 9309 governs matching.

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

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

Three front-loaded sentences with no filler; the core action leads and the anti-fetch constraint follows. The parameter blacklist is slightly long but earns its place by preventing a common wrong invocation.

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 read-only, 3-param tool with no output schema, the description covers the action, the non-fetching behavior, and the return shape (allow/disallow plus vendor stance). Nothing needed to call it correctly is missing.

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 ids, path, and robots_txt are already fully documented in the schema, setting the baseline at 3. The description reinforces the key constraint (robots_txt is contents, not a URL) but adds no syntax or format detail beyond what the schema provides.

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 verb (Match) and resource (a pasted robots.txt against Botcard's AI crawler tokens) with a named standard (RFC 9309). It is clearly distinct from siblings like get_crawler and list_crawlers, which retrieve crawler data rather than evaluate a pasted file. An agent can select this without opening the schema.

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

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

Explicit negative guidance — 'This tool does not fetch any website. Do not send url, host, target, website, robots_url, or fetch' — steers the agent away from the fetch-style misuse that the sibling tools might model. It gives clear context but does not name an alternative tool by name the way a top-tier definition would.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false; the description reinforces this by clarifying it performs no network fetch and returns stored card data. That adds useful context beyond the annotations, though it says nothing about auth needs, error behavior for unknown ids, or pagination.

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

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

Three compact sentences: the retrieval contract is front-loaded, followed by the negative constraint. No filler, no repetition of the title.

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 single-parameter, read-only lookup with no output schema, the description covers both the lookup key and the shape of the returned card (source URL, read date), and rules out misuse modes. Nothing needed to call it correctly is missing.

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

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

Schema description coverage is 100% and the id parameter is already documented with concrete examples (gptbot, google-extended), so the description only restates 'by id'. The negative enumeration of forbidden parameters is the one addition, but no id syntax, format constraints, or prefix conventions are supplied 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?

Specifies the verb (return), the resource (one card), and the retrieval key (by id), plus what the payload contains (vendor source URL and read date). An agent can distinguish this single-card reader from list_crawlers without opening either schema.

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

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

Explicitly states what this tool does NOT do ('does not fetch any website') and enumerates parameters it must not receive (url, host, target, website, robots_url, fetch) — a strong exclusion list. However, it never names the sibling tool an agent should call instead for fetching or listing, so routing guidance is implied rather than complete.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world. The description adds genuine behavioral context beyond them: no network fetch occurs, and each row carries the vendor page the summary was checked against, which tells the agent what kind of data comes back.

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

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

Three short sentences, purpose front-loaded, then return shape, then constraint. Each sentence earns its place; the middle sentence about the vendor page is slightly awkwardly worded but still informative.

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 zero-parameter, read-only list tool with no output schema, the description covers what it returns (crawler tokens, one per row with a vendor reference) and what it will not do (fetch). Sufficient for correct invocation, though more detail on row fields is absent.

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?

With zero parameters the baseline is 4, and the description adds useful value by explicitly forbidding invented arguments (url, host, target, website, robots_url, fetch) that an agent might otherwise hallucinate for a crawler-related tool.

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 verb and resource ('List the AI crawler robots.txt tokens in this dataset') and scopes it to the local dataset, which implicitly separates it from the fetching siblings. It does not name check_robots or get_crawler explicitly, so the differentiation is left partly to inference.

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?

'This tool does not fetch any website' plus the explicit do-not-send list clearly signals the usage context: read a static local list rather than probe a URL. The alternative (check_robots) is only implied, not named, so the routing guidance is good but not airtight.

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

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

Annotations already declare readOnly/no-destructive/idempotent/no-open-world, but the description adds real behavioral context: no network fetch occurs, the emitted file omits a User-agent: * group, and each group cites the vendor page. It never explains the tension between the verb "Write" and readOnlyHint (no external state is mutated), which is the one thing left implicit.

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?

Purpose is front-loaded and there is little filler, but the text is a chain of clipped fragments ("effect request_only means the vendor does not say the crawler obeys that line.", "control_token is not training.") that are hard to parse without prior domain knowledge. It is terse rather than 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?

For a no-output-schema tool with four optional params and solid annotations, the description covers output shape (no wildcard group, cited vendor pages), side effects (no fetching), and misuse constraints. It is slightly short on how `policy` interacts with `allow`/`block` when both are supplied.

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 does add a little meaning ("control_token is not training", the negative list of fields not to send), but its "effect request_only" terminology does not match any enum value (the enum has owner_requested), which adds confusion rather than clarity.

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?

Names a specific verb and resource ("Write a robots.txt") plus the scope ("for the kinds you allow or block") and the distinguishing output trait (cited groups). An agent can tell this apart from check_robots/list_crawlers without opening a schema.

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

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

The intended use is implied by the purpose statement, and the closing sentence gives a negative constraint ("Do not send url, host, target, website, robots_url, or fetch"). However, it never says when to choose this over check_robots or what prerequisite data ("this dataset") must exist first.

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