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

Annotations already declare idempotent, non-destructive, closed-world, non-read-only; the description adds genuinely new behavior: content is re-screened at approval time (a possible rejection path invisible in the schema) and only the API key that created the fax may approve it (an auth constraint). It stops short of saying what happens when re-screening fails or whether approval can be undone.

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?

Four short sentences, front-loaded with what the tool does, then the screening note, the auth rule, and the boundary against send_fax. No sentence is 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 two-parameter tool that already has full schema coverage, annotations, and an output schema, the description supplies the remaining lifecycle context (draft approval vs. sending, authorship requirement, re-screening) an agent needs to call it correctly.

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 fax_id and api_key are already documented, and the description's only parameter-relevant addition is the constraint that the api_key must be the one that created the fax. No format or value guidance is added beyond the schema, so baseline 3 applies.

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 plus the exact state it operates on (a fax DRAFT) and its consequence (so it can be transmitted). It also explicitly distinguishes itself from send_fax, so an agent can separate it from the transmission siblings without reading either 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?

The sentence 'Nothing is transmitted by this call — send_fax does that' is an explicit hand-off to the correct alternative, and the mention of DRAFT implies the create_fax_draft → approve_fax ordering. It does not spell out when approval should be skipped (e.g., already-approved faxes) or what preconditions exist beyond authorship.

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