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

Annotations already mark it readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description echoes that with 'Side effects: none (read-only).' It goes further by disclosing the race-condition behavior where an immediate 4xx is expected unless wait_seconds=30 is passed, and it instructs the agent on presenting status to the user in everyday language rather than raw fields. These are valuable beyond 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?

The description is compact and front-loaded with purpose, then the critical timing caveat, then the user-facing output guidance, then side effects. There is some redundancy with the schema's wait_seconds description, but each sentence earns its place and the structure is logical.

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?

With an output schema present and annotations covering the safety profile, the description covers the essential usage nuance (the 4xx race condition), the read-only nature, and the required user-facing formatting. Nothing an agent needs to call the tool correctly is 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 the baseline is 3. The description reinforces the wait_seconds semantics and adds the expected-4xx caveat, but the schema already documents the exact same 'pass 30 on first check, omit or 0 for later polls' behavior. No additional meaning is added for fax_id or user_id.

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 opens with 'Get details for a specific fax record,' a clear verb+resource action that identifies this as a single-record getter. It doesn't explicitly distinguish it from siblings like get-outbox-fax or get-fax-report, but the resource is specific enough that an agent can tell what it does.

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 gives concrete workflow guidance: after send-fax-uploaded, pass wait_seconds=30 on the first check, then omit or use 0 for later polls. It also warns that an immediate 4xx is expected without the wait. It stops short of naming alternatives or exclusions, so it isn't a full when/when-not guide.

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