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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds substantial context on top: the 100-path cap, the full list of evaluated crawlers, the lint categories (unsupported fields, 500 KiB limit, BOM, HTTP status semantics), the diff-only output shape when 'proposed' is set, and a concrete cost disclosure ('Each sitemap fetch costs one unit of the hourly budget'). The rate-limit/budget statement is exactly the kind of behavior an agent cannot get from annotations.

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 in sentence one, followed by input modes and then the return shape, so an agent can stop reading once it has what it needs. The paragraph is dense and packs several unrelated concerns (crawler list, lints, cost, diff behavior) into one block, but no sentence is wasted.

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 five parameters, the description fully compensates by describing the return payload (per-crawler verdicts, deciding rule and line number, lint list, flipped-verdict-only changes) and the fetching behavior. An agent knows what it will get back and what each mode costs without inspecting anything else.

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 every parameter is already documented with its interaction rules (content vs url, proposed semantics, use_sitemap cost). The description largely restates those same rules rather than adding new meaning; the only marginal addition is 'up to 100, or use_sitemap to read them from the file's Sitemap line', which is already implied by the schema. Baseline 3 applies 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 resource ('Validate a robots.txt with RFC 9309 and Google's parsing rules') and enumerates the scope of the output: per-path verdicts for eleven named crawlers, the deciding rule and line number, and lints. The robots.txt focus is distinctive enough to separate it from most siblings, though it never explicitly contrast itself with stillindexed_check_ai_crawlers or stillindexed_crawler_diff, which overlap on the crawler-verdict angle.

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 explains invocation modes clearly ('Give url to fetch the live file, or content to test a pasted one, plus proposed to diff a second version'), which tells an agent how to drive the parameters. It gives no guidance on when to prefer this tool over stillindexed_check_ai_crawlers, stillindexed_crawler_diff or stillindexed_check_url, leaving the sibling selection to inference.

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