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

Annotations already declare destructiveHint=true, so the agent knows this is destructive. The description adds important behavioral context: it verifies file sizeshare, lists missing/mismatched files in failures, and requires restarting on rejection. This goes beyond the annotation, but does not fully explain the destructive nature (e.g., what exactly gets destroyed) or potential side effects on the batch.

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?

The description is a single, dense sentence that front-loads the core purpose ('Finish a ... batch'), then includes the precondition, verification behavior, and failure handling. No wasted words; 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 tool with only 2 parametershare (both documented in the schema) and no output schema, the description covers the main operational steps: when to call, what it does, and what happens on failure. The only gap is that it doesn't explicitly state the return value (though the output schema is absent), but given the simplicity of the operation, it's reasonably 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 description coverage is 100%: both parameters (siteId and batchId) have descriptions. The description adds the cross-reference between siteId and start_revision, which is a useful nuance not in the schema. However, it doesn't elaborate on parameter formats or relationships beyond that, so it adds minimal extra value.

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?

The description clearly identifies the tool as the 'Finish' step for an upload batch begun by start_upload or start_revision, distinguishing it from abort_upload (its sibling that cancels). It specifies the action 'Finish' and the resource 'upload batch', which is unambiguous.

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 description states the precondition ('after every file has been PUT') and the consequence of failure ('must be started again'), which implies when to use it. It also references the sibling start_upload and start_revision by name, giving context. However, it does not explicitly mention when NOT to use it (e.g., if files are incomplete) or mention the alternative abort_upload, which could be a valid choice in some situations.

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