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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; 'It fetches nothing' is consistent with that rather than new information. What the description does add beyond annotations is real but secondary: the 30-day report retention (with null when none is kept), the one-sentence error format, and the fact that unrecognised override tokens surface in unknownOverrides. Useful behavioral context, though the description never says what happens to overrides that reference a crawler outside the three roles.

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 what is produced and from what input, then usage, then return shape — a sensible order. Slightly dense: the final sentence reads as a comma-chained list of return fields and the 'kept 30 days; null for tools that keep none' aside adds parenthetical clutter, but no sentence is wasteful.

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?

There is no output schema, and the description compensates fully by enumerating every result field (robotsTxt, contentSignal, decisions, unknownOverrides) plus the top-level summary and reportUrl, and by stating how errors are returned. For a drafting tool with four optional parameters and nested overrides, an agent has everything it needs to call it and interpret the response.

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 each parameter already names its enum values, the concrete crawler tokens in each role, and the defaults, so the description adds little beyond restating that roles are allowed-or-blocked and that overrides win over role choices — which the schema's own 'overrides' description already states. Baseline 3 is appropriate when the schema does the heavy lifting.

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 artifact ('Drafts robots.txt groups ... and a Content-Signal line') plus the input concept it works from, and implicitly distinguishes itself from the fetching siblings ('It fetches nothing'). The three crawler roles are enumerated, so an agent knows exactly what class of output this produces versus draft_llms_txt or draft_json_ld.

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 an explicit trigger and prerequisite: 'Use it after check_site_files or can_ai_fetch shows crawlers blocked or allowed against the owner's wishes.' It names the alternative tools by name and the condition that selects this one, leaving little to infer.

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