Complete document upload

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

Annotations already cover the safety profile (write, destructive, open-world), so the description adds the key behavioral facts: it is a terminal step that triggers asynchronous extraction, and it needs projects:write. It does not say what destruction means if called twice or on a bad key.

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?

Three short sentences, front-loaded with the action and precondition, with no filler. Every clause earns its place.

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 4-param mutation with no output schema, the description covers the sequencing, the side effect (extraction dispatch), and the required scope. What's missing is the async handoff (wait_for_document_extraction) and the three undocumented params.

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 25%, so only s3Key is partly explained (via the init link). filename, projectPid, and contentType are bare in both schema and description, and the description adds no format or constraint details. Baseline 3 is generous given the coverage gap.

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 (Finalize) and resource (presigned upload), and links it to its lifecycle predecessor air_upload_document_init and the uploadUrl PUT. An agent can tell this is the step-2 counterpart to init without opening anything else.

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?

The sequencing is explicit: finalize only after the PUT to uploadUrl succeeded, and it dispatches the extraction workflow. It does not name air_wait_for_document_extraction as the natural next step or state what to do if the PUT failed.

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