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

With no annotations, the description carries the full burden and does well: it enumerates every mutation it can perform (lang, charset, viewport, title, description, canonical, OG tags, lazy images, noopener, defer, alt), characterizes them as 'safe', and states the return value. It omits auth/permission requirements and whether fixes are reversible or idempotent, which keeps it short of a 5.

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-loaded with the action and resource, and the long fix enumeration earns its place by mapping to the schema enum. The two trailing sentences (return value, cost) are short and useful, though the middle sentence is dense.

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?

For a mutation tool with no annotations, no output schema, and low schema coverage, the description covers the two things an agent most needs: what will change and what comes back ('what changed and the new audit score'), plus cost. Missing prerequisites (ownership/auth, deployed-state requirements) are the main residual gap.

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 only 13% (just site_id), so the description must compensate. It does explain the meaning of each 'fixes' enum value, which is valuable, but it says nothing about the value-override params (lang, path, title, og_image, description, canonical_url) or their length/format constraints.

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 ('Apply safe automatic fixes') plus a precise resource ('an HTML page in a hosted site'), followed by an enumeration of the exact fix categories. An agent can immediately distinguish this from the read-only sibling site_audit, especially since the description says it returns 'the new audit score'.

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 only implied: the word 'fixes' and the mention of an audit score suggest running it after site_audit identifies problems, but no explicit when-to-use, when-not, or named alternative (site_audit, site_deploy) is given. The 'Cost: 2 credits per call' note is useful context but is not usage guidance.

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