confirm_upload

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the description builds on top by explaining the conflict error's meaning and the correct retry target — behavior an agent cannot infer from the schema. It stops short of saying whether a second confirm on an already-confirmed upload is a no-op, which matters given idempotentHint=false.

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, both load-bearing: the first defines the operation and its return, the second handles the single most likely failure mode. Nothing is repeated from the schema or annotations.

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 exists and the description still names the return ('returns the asset'), and the error path is covered, so an agent has what it needs to call and retry correctly. The one gap is the absence of any note on repeated confirmation behavior for a non-idempotent mutation tool.

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 description coverage is 100%, so upload_id, transform, and preset_key are fully documented in the schema, including that the transform 'runs before storage' and that preset_key is an alternative to transform. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 ('Finalises') and resource ('a presigned upload'), and ties itself into the workflow by naming the prerequisite state ('once its bytes are in storage'). This distinguishes it from create_upload_url (which mints the URL) and from the raw PUT, without the agent needing to guess.

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?

Explicitly states when to call it (after bytes land in storage) and gives concrete error-recovery guidance ('a conflict error means the bytes haven't landed yet: retry this call, not the PUT'). It does not contrast itself with sibling upload_file, which is the main remaining ambiguity.

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