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

Discloses the non-obvious two-step protocol the annotations cannot convey: the tool returns document_id/upload_url/upload_headers, the PUT must happen within 5 minutes, and document_id must reach create_fax within an hour. It also states that nothing is faxed or charged, which is the key reassurance for an agent worried about side effects, and is consistent with destructiveHint=false and idempotentHint=false (calling once per file avoids duplicates).

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?

Every sentence is load-bearing: purpose, ordering, return contract, timing windows, and the fallback. The critical fallback is front-loaded-adjacent rather than buried, and there is no filler.

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?

Even though an output schema exists, the description supplies the temporal and sequencing contract that the schema cannot express. For a five-required-parameter upload-prep tool with a mandatory follow-up upload, nothing an agent needs 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 coverage is 100%, so the baseline is 3, but the description contributes constraints absent from the schema: concrete size ceiling (20 MB) and the accepted formats. It also explains what document_id is for downstream, tying output values to the next call. Minor omission: HEIF is in the enum but not listed in the prose format list.

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 ("add a file ... to a fax") and immediately scopes the artifact types accepted. It is clearly distinguishable from create_fax and send_fax, which are the natural siblings an agent might confuse it with.

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 ordering ("call it once per file, before create_fax, in the order the files should be faxed") and an explicit negative case: if the bytes can't be read, call create_fax without document_ids instead. Both the when and the when-not are named, plus the alternative path.

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