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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=true), and the description adds genuinely new behavioral context: the upstream sources (Crossref, OpenAlex, arXiv), the presence of a retraction flag, and the explicit scope limit "No abstracts." It stops short of describing what happens on a failed lookup (error vs. empty result) or whether multiple candidate matches are returned, 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?

Two tight sentences with the purpose and accepted identifiers front-loaded and the scope caveat ("No abstracts") at the end where it belongs. Nothing is repeated from the annotations or the schema, and no sentence is wasted.

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?

Because there is no output schema, the description usefully enumerates the return fields, which is exactly what an agent needs to judge the result. The only real hole is the undocumented `year` parameter and the absence of not-found/ambiguity behavior, both minor for an idempotent read-only lookup tool.

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 50%, so the schema documents only doi (including arXiv ids) and author; the description adds the useful combinatorics that title should be paired with author. The `year` parameter is left completely undefined in both the schema and the description, so an agent cannot tell whether it is a filter, a disambiguator, or required for date-sensitive checks.

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 opens with a specific verb and resource ("Check that a paper exists") and immediately states the returned metadata fields (title, authors, year, venue, DOI link, retraction flag). It also names the accepted identifier types (DOI, arXiv id, title plus author), so an agent can distinguish this citation-verification tool from siblings like verify_links or package_check without opening any 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?

Usage is implied through the three input modes and the hint that "A surname helps" when searching by title, but there is no explicit statement of when to prefer this over alternatives or when not to call it. For example, it doesn't say whether a bare title with no author is acceptable or will be rejected, leaving the agent to infer call conditions.

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