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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it discloses that results derive entirely from already-computed crawl data with no new work, that TLS checks are deliberately unbuilt and surfaced via notDerivable, that homepageStatus.redirectsToHttps is null rather than assumed healthy, and that the call is free with no external call. This is exactly the 'checked vs never checked' nuance an agent cannot get from structured fields.

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 report contents before the caveats, and each caveat (unbuilt TLS checks, null redirect status) carries real decision value. It is dense and slightly overlong with stacked parentheticals, but no sentence is pure filler.

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?

There is no output schema, so the description carries the full burden and does so: it enumerates returned fields (notDerivable, homepageStatus.redirectsToHttps, state), explains their semantics, and covers the safety profile already implied by annotations. An agent has everything needed to interpret the response.

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 auditId and projectId are already documented in the schema, including that omission means the latest completed audit. The description only loosely echoes this ('latest completed crawl (or a named earlier one)') and adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

Names a specific resource (HTTPS report) and enumerates exactly what it contains: secure-page percentage, mixed-content and insecure-link counts, homepage HTTPS-path status, and HTTP URLs in the sitemap. Scoped to a project's latest or named crawl, which cleanly separates it from siblings like get_audit_core_web_vitals and get_audit_internal_links.

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?

States the prerequisite flow ('narrow on state first: no_audit vs analysed') and the auditId omission behavior, giving clear context for when the call is meaningful. However it does not name a specific alternative report tool or explicitly state when-not-to-use, so it stops short of full routing guidance.

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