check_retractions

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the data provenance (Crossref carrying Retraction Watch) and the breadth of notice types, which the schema does not convey. However, it says nothing about permissions, rate limits, latency (a per-paper Crossref lookup), or whether missing papers are returned as clean rather than unlisted.

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?

Three tight sentences: what it returns, from where, how to feed it, and how it relates to a sibling. The core resource and source are front-loaded with no redundant padding.

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 low-complexity lookup with no output schema and no annotations, the description covers inputs, data source, and notice categories adequately. The main gap is the shape of the result (per-paper flags vs. a notice list), which matters for an agent interpreting the response, but the tool's simplicity keeps this a minor omission.

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 67%, with 'dois' left undocumented in the schema. The description restates the three accepted input forms and adds that corpus_file originates from import_records, which is genuine added meaning. Beyond that it does not clarify precedence when multiple inputs are given, or formatting expectations, so it does not fully compensate for the coverage gap.

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 names the concrete resource (retraction notices: retractions, withdrawals, expressions of concern, corrections) and the scope (a set of papers), plus the upstream source (Crossref / Retraction Watch). It is not phrased as a verb+resource, but an agent can immediately tell this is a retraction-status lookup. It also distinguishes itself from citation_network, which covers the same check.

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?

It gives explicit input options ('Give DOIs, Scopus IDs, or a corpus_file from import_records') and clarifies its relationship to citation_network, which already runs the check on every network — implying when this standalone call is redundant. It stops short of an explicit when/when-not statement, so it is strong context rather than full routing guidance.

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