Read paper text

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

Goes well past the annotations: discloses metered TEI XML retrieval on first call, local reuse on continuations, bounded passage size, provenance in the response, incomplete full-text extraction, explicit abstract-only labeling, and a prompt-injection warning about treating text as source material. These are exactly the behavioral facts the readOnly/openWorld/non-idempotent hints cannot convey.

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 and identifier forms, then progressively adds caveats; every sentence carries operational meaning except the 8000-character default, which duplicates the schema's limit description.

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?

Output schema and annotations already cover return shape and safety profile, and the description fills the remaining gaps an agent needs: identifier acceptance, continuation mechanics, metering, extraction incompleteness, and the abstract-only caveat.

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; the description still adds value by tying continuation to next_args replay and clarifying that the same identifier must be retained across replays, which the schema only states tersely. The 8000-character default merely restates the schema but the continuation semantics go beyond it.

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 (read a bounded passage of structured OpenAlex full text) with the accepted identifier forms, which cleanly separates it from article_download (whole-file retrieval) and article_details (metadata). An agent can pick this tool without inspecting 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?

Explains the first-request vs continuation flow ('continuations reuse verified local content', 'next_args to replay unchanged') and warns that abstract-only availability must not be treated as reading the whole paper. It lacks explicit routing to siblings like article_download when a full download is wanted, so it stops short of full when/when-not coverage.

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