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

Annotations already mark it destructive and not read-only. The description adds useful behavioral details beyond that: it returns presigned PUT URLs rather than uploading directly, deletePaths operates within the same revision, and finalize_upload is the required follow-up. No contradictions with annotations.

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?

Two sentences with no filler. Purpose, return behavior, and continuation step are all front-loaded, and every sentence adds operational information.

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 moderate-complexity tool with no output schema, the description gives the essential call flow: presigned URL outcome and the mandatory finalize_upload follow-up. It doesn't specify the exact shape of the returned URL map, but an agent can invoke the tool correctly with the schema and this high-level contract.

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?

Only siteId is described in the schema, so the description carries some weight. It adds semantics for deletePaths ('removes files in same revision') and connects files to presigned PUT URLs, but it doesn't explain path/sizeBytes/contentType requirements; the nested schema descriptions compensate for that detail.

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?

Description names a specific verb ('Start updating') and resource ('EXISTING site'), then sharpens it with behavior ('returns presigned PUT URLs', 'deletePaths removes files'). This makes the tool's role distinct from start_upload/update_site without needing to open the schema.

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?

Clearly frames when to use it (updating an existing site) and gives an explicit workflow handoff ('Complete with finalize_upload, passing the same siteId there'). It doesn't explicitly exclude alternatives like start_upload for new sites, so it stops short of a full when/when-not statement.

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