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

Annotations already cover readOnly, idempotent, and openWorld, so the bar is lower; the description still adds real context by naming the four signal types inspected and clarifying that it covers 20 crawlers split into search/user vs training categories. It omits pacing/rate-limit behavior and what a failure report contains, which keeps it from a 5.

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 core capability is front-loaded in the first sentence, with the differentiating crawler-classification note and the free/no-key/docs line following as short support. The crawler list ('and 14 more') is slightly padded but carries genuine scope information.

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, the description should convey the shape of the result (per-crawler allow/deny verdicts plus the rule that caused it), but it only says what is evaluated, not what comes back. For a diagnostic tool with 20 crawlers and multiple rule sources, an agent cannot predict the response structure from this text alone.

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 only two parameters, so the schema already documents url and path fully, including the https:// normalization and the path override. The description adds no further detail about how `path` interacts with the URL's own path or what happens when a site-level vs page-level check is requested.

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 uses a specific verb (checks) plus a concrete resource (whether named AI crawlers may read a page) and enumerates the exact evidence sources: robots.txt RFC 9309, robots meta, X-Robots-Tag, and firewall user-agent refusal. It is clearly distinguishable from siblings like validate_llms_txt or check_structured_data, which target different artifacts.

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?

Usage is implied rather than stated: the note that search/user crawlers 'decide whether you can be cited' hints at when this matters, but there is no explicit 'use this when…' or exclusion against run_aeo_audit or score_answer_readiness. The 'Free, no key' note removes a prerequisite question but is not routing guidance.

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