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

Annotations already flag destructive/openWorld/not-idempotent, but the description adds the crucial async semantic that annotations cannot express: 'Success means queued/submitted only—not delivered,' plus the note that paths can be reused across sends. The 'Side effects' line confirms outbound queueing for delivery, matching rather than contradicting 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 action and its precondition, then constraints, then success semantics — a good ordering with no filler sentences. Minor redundancy: 'to must be an array' and path reuse duplicate what the schema already says, costing a little tightness in an otherwise efficient paragraph.

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 11-parameter, nested-object, non-idempotent mutation tool, the description covers the whole operator journey: where files come from, what not to pass, that only queueing is confirmed, and how to poll status. With a full schema and an output schema present, no additional detail is required for correct invocation.

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 100%, so the baseline is 3; every parameter including nested cover_page/options is already documented in-schema. The description only adds marginal operator guidance — 'to must be an array' and 'same paths may be reused for multiple sends' — which largely restates the schema's array/E.164 notes.

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 — 'Queue a new outbound fax using storage paths' — and immediately scopes it to a particular input mode (storage paths, not bytes or local paths). It distinguishes itself from the MCP Apps UI flow and points to get-fax/get-outbox-fax for status, so an agent can separate it from resend-fax and the widget path without opening a schema.

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?

Gives explicit preconditions ('after an agentic request-file-from-user curl ... or after upload-file'), an explicit exclusion ('Do not call this after the MCP Apps UI flow — the widget already sent'), and a negative constraint ('Do not pass local filesystem paths or file bytes'). The follow-up path is also named: check status with get-fax or get-outbox-fax using the returned id.

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