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

Annotations already cover readOnly/idempotent/openWorld, and the description goes well beyond them by disclosing the full result vocabulary and, critically, warning that 'lookup_failed' means the DOI could not be checked and is 'not a clean result'. That failure-mode distinction is exactly the kind of behavioral context an agent needs to avoid misreading output.

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-loads purpose, then the status list, then the scale note. The long status enumeration is dense but each token carries meaning for interpreting results. Slightly list-heavy but no wasted sentences.

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, so return structure needn't be explained, yet the description still supplies the status semantics needed to interpret results. For a single-parameter, read-only lookup tool this is fully sufficient.

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?

Only one parameter, and the schema description already covers both accepted forms (bare DOI or https://doi.org/ link) at 100% coverage. The description adds no additional format or batching detail, so the baseline 3 applies.

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 ('Check DOIs for retractions, expressions of concern and corrections') and names the data source (Crossref incl. Retraction Watch). The enumerated status vocabulary makes it clearly distinct from sibling verify_references, though no sibling is named explicitly.

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 scope is implied by 'Works for a single paper or a whole reference list', which tells the agent this handles both single DOIs and bulk lists. However, there is no guidance on when to prefer this over verify_references or how it fits with the other reference-checking siblings.

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