Upload service file

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

Annotations already declare destructive/non-idempotent/write semantics, but the description adds substantial context beyond them: SHA-256 computed and verified after atomic commit, a 3-open-upload cap with aborts freeing slots, exec-equivalent path refusals (filesExecEquivalentScopeMissing), required scopes (files:manage on FULL access, vm:files:write), 423 on 2FA lock, and availability gates with verbatim reason codes. It earns credit for going well past 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 action and then densely packed with genuinely load-bearing constraints, so little is wasted. The middle sentences are long clause chains that could have been split or bulleted without losing 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?

No output schema exists, and the description compensates by stating what comes back (the final answer, or an operationId after waitSeconds). Combined with the permission, availability, and safety constraints, an agent has everything needed to invoke this correctly on the first try.

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 67%, and the description supplies the meaning the schema leaves implicit: when expectedVersion applies, what waitSeconds returns on expiry, that mode applies only to a NEW file, and that overwrite replaces rather than creates. It does not explain confirmSystemPath's 409 behavior (already in schema) or how mode interacts with overwrite, so it is strong but not exhaustive.

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 ('Upload a file to the server') and names the two input sources (localPath or contentBase64), plus the resumable/chunked/atomic pipeline, so the agent can tell it is the full upload path rather than a plain write. It never names its closest sibling (write_service_file), so the differentiation from that alternative is left to inference.

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?

Explicit routing rules: use overwrite=true with expectedVersion from stat_service_file when replacing; after waitSeconds expires continue with get_service_file_operation and 'never repeat the call'; relay unavailability reasons verbatim and 'never work around it'. These are concrete when-to-use and when-not-to-do-something instructions.

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