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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is settled. Beyond that, the description discloses the non-obvious polling state machine: added=false with empty documents until the user presses 'Done adding pages', and the requirement to re-invoke. It stops short of stating timeout behaviour or what happens if the user abandons the link, which keeps it off a 5.

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 clause carries real information, but the prose is one dense run-on written in a folksy second person ('answers the documents it put on their draft, ready to send, with their pages') that takes re-reading to parse. The most important constraint, the re-call loop, is buried mid-paragraph rather than front-loaded. Tightening into discrete sentences would cost nothing in content.

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 single-parameter polling tool with an output schema that already defines added, documents, and ask, the description supplies the missing operational context: when to call, when to prompt the user, when to retry, and where the ids go next. Only edge cases (user never finishes, link expiry, duplicate ids) are unaddressed.

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?

There is one parameter with 100% schema description coverage, and the schema already says link_id is 'The link, as add_fax_file_link gave it.' The description's reference to 'the address add_fax_file_link gave' restates that without adding format, length, or provenance detail. Baseline 3 applies when the schema does the semantic work.

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 pins the tool to a specific resource: it 'answers the documents it put on their draft, ready to send, with their pages', and it names the sibling that created the link (add_fax_file_link) plus the sibling that consumes the result (send_fax). An agent can tell this apart from add_fax_file and send_fax. It loses a point because the phrasing is convoluted and never states the core purpose in a single plain clause.

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 trigger ('Once the person says they're done adding their pages'), an explicit not-yet branch ('there are no documents, and ask says what to ask of them'), the exact retry instruction ('then call again'), and the handoff ('Give send_fax their ids ... in the order you added them'). Both when-to-use and what-to-do-otherwise are covered, which is rare.

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