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.