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

Annotations already cover safety and idempotency, so the description's real contribution is the default response composition (question, answer, summary, limitations, anchored sections) and the standing instruction to carry limitations through. It does not say what happens when a paper identifier does not resolve, which is the notable 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?

Front-loaded with the retrieval action and identifier forms, then the default response, then the format modes. Dense and mostly waste-free, though the mode sentence partly duplicates the schema's own format and section descriptions.

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, the description needn't enumerate return fields, yet it usefully characterizes the summary payload and the always-present citation. It leaves out error behavior for unknown slugs and any pointer to list_papers for discovering identifiers.

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 schema already documents the identifier forms and the format enum. The only added nuance is that selecting a section returns just that section, which is a small clarification of how format and section interact rather than new meaning.

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?

"Retrieve one Capital Made Physical paper by slug, CMP number or canonical URL" gives a specific verb, a specific resource, and the accepted identifiers. It is clearly singular-retrieval, which contrasts with the listing/search siblings without naming them.

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 explains what each mode returns but never says when to reach for this tool versus cite_paper, search_research or list_papers, nor how to obtain a valid slug. Usage is implied only by the existence of the format switch.

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