Doorman

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

Annotations already declare read-only, idempotent, open-world and non-destructive, so the description only restates "Read-only" briefly. Its added value is real: it discloses that the fetch is live, that results come grouped into four bot categories with partial-block states, and that fixes are included. It does not cover edge behavior such as an unreachable site or a missing robots.txt.

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?

Front-loaded with the triggering user question, then behavior, example, safety note, and sibling hand-off — every clause carries information. It is dense in one long opening sentence, but nothing is filler.

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?

No output schema exists, and the description compensates by describing the report's structure (four bot groups, three access states, content-signal preference, fixes). What is missing is failure-mode behavior for unreachable sites or absent robots.txt files.

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% with a single required param, so the baseline is a 3. The description adds a concrete invocation example ({"url": "example.com"}) showing that a bare domain without scheme is acceptable, which meaningfully reduces call-format 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 verb and resource ("Fetches the live robots.txt and reports") with concrete scope: 22 named AI bots in four groups plus content-signal preference. This is clearly distinct from doorman_write_robots_txt and doorman_check_robots_txt.

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?

Gives explicit trigger phrasings ("whether their site blocks ChatGPT, Claude...", "why AI search does not mention their site") and routes the write case to the sibling tool by name. Nothing is left to inference about when to pick this versus the 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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds meaningful behavioral context beyond that: it parses like crawlers do (groups, wildcards, longest-match), reports each bot as let in, kept out, or partly blocked, and provides notes plus a suggested choice. It does not mention size limits or exact output structure, but the key behavior is well disclosed.

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 front-loaded with the usage condition, then explains parsing behavior and output, and ends with a compact example. Every sentence contributes useful context without redundancy.

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 one-parameter parsing tool with no output schema, the description is complete enough to invoke correctly. It explains the input format via example, the parsing semantics, the expected report categories, and that no network access occurs.

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

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

Schema coverage is 100% and the single parameter is already well documented as the full robots.txt text up to 512 KB, with empty meaning no robots.txt. The description includes a helpful example of the parameter shape, but it does not add substantial semantic meaning beyond what the schema already 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?

The description states a specific action: parsing pasted robots.txt text and reporting which of 22 named AI bots are allowed or blocked. It clearly distinguishes this pasted-text parsing tool from siblings like doorman_check_ai_bot_access and doorman_write_robots_txt by emphasizing 'Pure parsing, no network.'

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?

It gives a clear when-to-use condition: the user pastes robots.txt or has drafted one and asks which AI bots it lets in or blocks, or whether a change works. It does not explicitly name alternative sibling tools or state when not to use this one, so it falls short of full when/when-not/alternatives guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world behavior. The description adds useful behavioral detail beyond the annotations: it preserves existing rules, adds one clean group per choice, includes a shared content-signal line, and returns text without modifying the site.

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 front-loaded with the usage condition, then explains inputs, gives a compact example, and states the return value. Every sentence earns its place and there is no unnecessary repetition.

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 and fully covered: annotations carry the safety profile, the schema documents all four parameters, and the description explains the generated output and that no site is changed. Nothing material is missing 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?

Schema description coverage is 100%, so the schema already documents the parameters, defaults, and enum values. The description reinforces the three group choices and mentions the optional existing robots.txt, plus an example, but does not add much 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?

The description states a specific verb and resource: writing robots.txt with AI bot choices. It clearly distinguishes the tool from the sibling check tools by emphasizing that it returns a complete robots.txt to paste and does not change any site.

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 first sentence gives a clear when-to-use condition: the user wants to allow or block AI training, AI search, or assistant bots and needs the robots.txt lines. It does not explicitly name the sibling check tools as alternatives, but the generation-vs-checking distinction is clear.

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