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

Annotations declare the safety profile (not read-only, not idempotent, not destructive), and the description adds genuinely non-inferable behavior: a $0.01 per-call cost with no charge on failure. It does not explain the outcome artifact (a new stored file plus a time-limited link), which is the main remaining gap.

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?

Two short sentences, result stated first, cost second. Every clause carries information; nothing is redundant with the title.

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 non-idempotent write with no output schema, the definition leaves out what is returned (new file id / download link) and what link_hours controls, even though the parameter itself is undocumented in the schema. Adequate to call, but an agent cannot predict the response.

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 33%: name and file_ids are documented, link_hours has no description anywhere. The description contributes a real semantic detail the schema lacks — that file_ids order determines output order — which lifts it above a bare baseline despite the undocumented link_hours.

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 ('One PDF from several in the store') and adds a distinguishing detail, that input order is preserved, which separates it from documents_create_pdf or documents_convert_to_pdf. It stops short of naming those siblings explicitly.

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?

'in the store' implies a precondition (sources must already exist, i.e. via files_upload), but the description never states when to merge versus creating a PDF or converting one. No alternatives are named, so the agent must infer usage from the name.

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