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

Annotations already declare a safe, idempotent, open-world read, so the description only needs to add beyond that. It does: it discloses the crawl budget ('Reads up to 10 public pages') and a genuine failure mode ('A site that turns away automated readers cannot be scored'), both of which an agent needs before invoking.

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-loads the core action and score scale, then the trigger condition, then the crawl limit and precondition. Four sentences that each add something, though the five-criterion enumeration makes it slightly long for the payload it delivers.

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 naming the 0-100 scale and the five scored dimensions, giving the agent a sense of the return. The precise output shape and whether the ten-page result set is itemized remain unstated, keeping it short of complete.

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 both url and lang are already documented in the schema, including the enum guidance in lang. The description adds nothing about parameter format or behavior beyond 'any public site'. Baseline 3 is appropriate when the schema carries the full parameter burden.

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 ('Scores any public site out of 100') and enumerates the five concrete dimensions being scored (crawler access, llms.txt, schema/entity clarity, quotability, dates and sources). This clearly distinguishes it from narrow siblings like check_llms_txt or check_counter_installed, which each probe one of these facets.

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?

Explicit trigger condition: 'Use it when someone asks whether ChatGPT or another assistant can read and quote a site.' It also states an exclusion ('A site that turns away automated readers cannot be scored'). It does not name a sibling alternative for follow-up actions, but the when-to-use guidance is unambiguous.

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