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

With no annotations, the description carries the full burden and does disclose two non-obvious traits: the operation is asynchronous (returns job_id to poll) and it consumes account credits. It does not cover auth/permission needs, failure behavior on incompatible format pairs, or credit amounts.

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 tight sentences, front-loaded with the action, then preconditions, return value, and cost. Every sentence carries information an agent needs before calling.

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 an 8-parameter tool with a nested object and no output schema, the description covers the async return contract and the cost side effect, which is what the agent most needs. It is slightly incomplete on the mutual exclusivity of the extension-based vs numeric-id format parameters.

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 the parameters are already well documented and the baseline is 3. The description restates the source_format/target_format extension convention but adds nothing about the *_id alternates, format_type/format_type_id precedence, or what additional_arguments accepts.

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 gives a specific verb+resource (starts a conversion of an already-uploaded file) and constrains the input to a file_id already in FileConvert. This implicitly separates it from convert_file, which handles not-yet-uploaded files, though it never names that sibling outright.

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?

It states the precondition clearly (file_id must come from upload_file or a previous job) and names the follow-up tool (get_job_status) for polling. It stops short of an explicit when-not/alternative branch naming convert_file, so it is clear context rather than full routing guidance.

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