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

Annotations already establish that this is a safe, idempotent, read-only operation, so the description's added value is the output contract: severity ordering, per-problem pages/why/fix, and a readable checklist. What it omits is operational behaviour — that it fetches the live site (latency, possible failures) and when site_token is required for anonymous deploys.

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?

A single tight sentence that front-loads the verb and resource, then enumerates the output shape without filler. Every clause carries information an agent needs to decide to call it.

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?

The output schema exists, so return values needn't be re-explained, and the description is adequate on scope. It is still thin for a live-site fetch: no note about cost/latency, authentication via site_token, or how a single-page path interacts with the area-based scan.

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 75%, so the schema largely documents the parameters. 'Measured problems by area' loosely ties to the areas enum list, but the description adds no meaning for path (single-page scoping) or site_token (secret for anonymous deploys) beyond what the schema already states — the baseline 3 applies.

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?

Specific verb+resource ('Checks a live site') followed by a precise account of the returned artifact: problems by area, severity-ordered, with pages, rationale and fix, plus a checklist. This clearly separates it from retrieval siblings like get_site or get_analytics, though it never names a sibling explicitly.

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 by 'live site' and 'checklist to judge by reading', suggesting an audit of a deployed site rather than stored metadata. There is no explicit when-to-use/when-not statement and no pointer to alternatives such as get_site or get_analytics for plain data retrieval.

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