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

Annotations declare it is a non-read-only, destructive (credential-creating) operation, and the description adds materially beyond that: the key is returned exactly once, must be treated as a secret, should not be echoed to the user unprompted, and must be persisted in client/session storage for reuse. That is exactly the behavioral context an agent needs before invoking.

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 purpose, then the optional parameter, then the secret-handling and reuse protocol. Every sentence carries a distinct instruction, though the four-sentence density is near the upper bound for a single-parameter tool.

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?

An output schema exists, yet the description still flags the one non-obvious return fact (attributes.key is single-use output). Combined with lifecycle guidance (store, reuse, re-call on 401/403) and consumption instructions, nothing an agent needs to call this correctly 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?

Top-level schema coverage is 0% (the single 'body' param carries no description), so the description must compensate, and it does: it names api_key.description as the optional field and clarifies that user_id is unnecessary under OAuth, matching the nested schema's note. It stops short of covering the full nested structure, so it compensates well but not exhaustively.

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 ('Generate a Common Paper API key for the current OAuth user'), plus the optional label it accepts. No sibling tool generates credentials, so an agent can place it uniquely in the toolset without opening the 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?

Explicitly states when to call it and, more importantly, when NOT to call it again: only re-invoke if a request fails with 401/403 or the stored key is missing. It also names the consumption pattern (Authorization: Bearer for direct HTTP calls such as POST /v1/attachments), leaving no ambiguity about sequencing.

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