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

Annotations already declare non-readonly, non-idempotent, non-destructive. The description adds a real behavioral fact — the file is persisted for fax delivery — which is useful context beyond the annotations. However, it omits size limits, format restrictions, expiration of the stored file, and any permission/auth notes, leaving meaningful gaps for a mutation tool.

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 short, front-loaded sentences with no filler: the action first, then the sequencing requirement and side effect. Nothing redundant.

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 pipeline step with full schema coverage and an output schema, the description covers the essential contract: bytes in, path out, then hand the path to send-fax-uploaded. Only auxiliary constraints (max size, supported formats, file lifetime) are missing.

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 every parameter including format, mime_type, user_id and pipeline_id is already documented in the schema. The description adds no parameter-level detail beyond that, which is acceptable at baseline but earns no extra credit.

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+resource ('Upload document bytes as base64') and names the required follow-up tool, which distinguishes it from siblings like get-file or request-file-from-user. It doesn't explicitly contrast with those siblings, but the pipeline-sequencing detail makes its role 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 does say what to do next ('then call send-fax-uploaded with the returned path'), which is genuine usage guidance. But it never states prerequisites (pipeline_start is only mentioned in the schema) or when not to use this versus other upload/request paths.

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