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

Annotations already declare readOnly, idempotent, open-world, non-destructive behavior, and the description usefully adds scope limits: static-only analysis, refusal of private/localhost/HTTP targets, and an explicit non-exhaustive caveat. It does not disclose rate limits, payload size caps, or timeout/fetch-failure behavior, which matter for a live network fetch.

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?

Three sentences, front-loaded with capability, then trigger, then boundaries. Every sentence carries distinct information with no redundancy.

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?

An output schema exists, so return values need not be described. The description covers what the tool does, when to use it, what targets are refused, and what it explicitly does not measure — sufficient for an agent to call it correctly.

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 all three parameters (url, focus, minPriority) are already fully documented with enum options and defaults. The description only restates the HTTPS-only constraint already present in the url schema, adding no new parameter meaning.

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 a public HTTPS page and performs a non-exhaustive static review of its HTML') plus the output shape ('prioritized issues and fix guidance'). This clearly separates it from the rule-lookup and reference siblings, which do not fetch or analyze live pages.

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 ('when the user requests an audit of a deployed public page') and clear exclusions (no localhost, private networks, or plain HTTP; no execution, Core Web Vitals, or accessibility certification). It stops short of naming the overlapping sibling review_code as the alternative for local/source-level analysis.

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