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

It adds real context beyond the annotations: a short-lived fax-scoped token is minted, the UI uploads and sends only on user click, the UI does not post a chat message but injects the fax ids into context, and file bytes must never be read or passed. It still does not say what happens if the user closes the panel, whether the token expires, or whether a partially completed upload can be retried -- meaningful gaps for an operation annotated destructive.

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?

Individual sentences are purposeful and rules are stated imperatively rather than padded, but the whole thing arrives as one undifferentiated block with no opening statement of purpose and no separation between ordering rules, parameter rules, and mode handling. Front-loading the three-mode branching (Apps / unconfirmed / agentic) would make it far easier to scan.

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?

Given seven parameters, a required ordering protocol, three client-capability modes, and an output schema, the description covers everything an agent needs to invoke it correctly: what to gather first, what to pass, which modes exist and what to do in each, and where to go next once a fax_id is known.

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 schema already defines to/from/numbers/contacts/pipeline_id/start_file_upload, including the array item shapes; the description largely restates those rules. It does add the sequencing constraint that numbers and contacts must be passed through from the listing calls unchanged and that to/from are prefill-only, which is modest value on top of the schema.

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 conveys the specific resource and action -- it collects sender numbers, contacts and pipeline_id so the UI can upload a file and send a fax, and it explicitly separates itself from upload-file and send-fax-uploaded. It never states a single front-loaded purpose sentence, though, and the name (request-file-from-user) is never reconciled with the behavior described (a fax-send orchestration step).

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 gives an explicit call order (pipeline_start, then list-numbers and list-contacts, then this tool), states what must not be re-done inside the tool, and names the alternatives it forbids in Apps mode (send-fax-uploaded, upload-file) versus the one it requires in agentic mode. When-to-use and when-not-to-use are both spelled out.

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