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

Goes well beyond the annotations (destructive, non-idempotent, non-readonly) by disclosing atomic publication as a new version, the post-deploy constraints (root index.html, 200-file cap, plan size limits, 4 MB per call), that a non-live deletePath is refused with its name, and that exhausting the deployment allowance degrades to an unpublished draft with published=false. That is the exact set of failure modes an agent needs for a destructive mutation.

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 operation in the first clause, then spends the paragraph on quantitative constraints and edge-case behavior. Every sentence carries a distinct, actionable fact (atomic publish, draft fallback, refusal rule) with no 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?

For a destructive mutation tool with no output schema, it supplies the safety-relevant behavior and failure modes. It does not describe the overall response shape (beyond the published flag) or any authorization prerequisites, which keeps it just short of fully complete.

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 already documents path format, encoding, and message. The description adds real semantics the schema lacks: files replace the live file at the same path, deletePaths must correspond to live files or the call is refused, and the total payload is capped at 4 MB per call. siteId and message semantics are left to the schema.

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 ('changes some files of a live site') and immediately delimits scope: files added or replaced, deletePaths removed, everything else untouched. This clearly separates it from full-deploy siblings like deploy_site and from update_site without requiring the schema to be opened.

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?

Makes the operative condition clear: the patch starts from the live version, never an unpublished draft, so it is the partial-update path rather than a full deploy. It does not explicitly name deploy_site or update_site as alternatives or state when a full deploy is preferred, so the alternative routing is implied rather than stated.

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