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

Annotations declare destructiveHint=true and idempotentHint=false, and the description explains the actual consequence: concurrent writes can be lost, with expected_content_sha256 turning that into a FAILED_PRECONDITION instead of silent overwrite. It also discloses the downstream effect that a republish is required to push the change to the CDN — real behavioral context not present in the 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?

Front-loaded with the core semantics and alternatives before the recovery procedure, which is the right order. It loses a little to redundancy — property-order preservation is asserted three times across the description and the schema, and the patch_datafile recommendation appears twice in slightly different forms.

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?

An output schema and full annotation set already cover returns and the safety profile, so the description's job is the mutation semantics and failure modes — both covered. The concurrency guidance, the patch alternative, and the republish requirement are everything an agent needs to call this correctly.

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 100%, so the baseline is 3, but the description adds genuine meaning on top: `json` replaces the entire document versus per-field metadata updates, and expected_content_sha256 is framed as part of a get → edit → send round trip with an explicit do-not-retry-the-same-json rule. The remaining parameters are left to the schema, which already documents them well.

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 and immediately qualifies the scope: field-level partial update of metadata, whole-document replacement when `json` is supplied. It explicitly distinguishes itself from the sibling patch_datafile, so an agent can route correctly without opening either 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?

Gives explicit routing rules: use patch_datafile to change part of an existing document, use this tool when replacing the whole document anyway. It also states when to omit `json` (metadata-only) and when to omit or supply expected_content_sha256, including the 'blind overwrite is fine when nothing else writes this datafile' case.

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