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

Annotations only cover readOnly/openWorld; the description adds the genuinely non-obvious trait that the page is re-read live and 'never a cached result', plus the tri-state result vocabulary (passed / failing / not_measured). That is exactly the kind of behavioral detail annotations cannot convey.

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 tight sentences: purpose first, then the freshness guarantee, then the usage precondition. No filler, and the most decision-relevant facts are front-loaded.

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 carries the return-value burden and does state the per-code verdicts. The meaning of 'not_measured' is left implicit, a minor gap for an otherwise simple three-parameter read tool.

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 url, lang and codes are already documented in the schema; the description only reinforces the origin of the codes. Baseline 3 applies since the description adds no format or syntax detail beyond the structured fields.

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 outcome ('Confirm that a fix worked') and immediately distinguishes itself from siblings by naming audit_url and geo_check as the sources of the codes it consumes. An agent can tell this is the post-change verification step, not the audit step itself.

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 explicit sequencing ('after you change the page') and routes the agent to the two sibling tools that produce valid codes. There is no explicit when-not-to-use statement (e.g. don't call before editing), so it stops just short of the top band.

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