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

Annotations only mark it as non-read-only/non-destructive; the description adds substantial behavior beyond them: asynchronous execution returning a tool_job hashid with status 'queued', the required polling loop via get_tool_job_status, per-day rate limits, a per-file size cap, and self-explaining limit errors.

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-loads purpose and the free/paid distinction, then workflow, then per-operation params, then async behavior. Well-organized with bullets, though slightly dense and mildly repetitive about the free path.

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 async tool with no output schema, it fully covers what an agent needs: input flow, operation params, the queued job return shape, how to poll for completion, and where the final output URL appears.

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 already 100%, so the baseline is 3. The description adds real value by grouping parameters per operation (compress: quality/format; resize: width/height/optional format; crop: aspect OR x/y/width/height) and clarifying the mutually exclusive crop inputs, which the flat schema does not express.

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 ('Edit an already-uploaded image file') and enumerates the three operations (compress, resize, crop). It is readily distinguishable from siblings like edit_video and complete_upload by naming image editing and the operations it covers.

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?

Provides explicit when-to-use context (free, only needs an account, no subscription) and an explicit exclusion: 'Do NOT call complete_upload (that starts the paid clip pipeline).' It also prescribes the exact alternative workflow (create_upload, PUT bytes, pass id) and routes polling to get_tool_job_status.

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