check_retractions

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

Annotations already carry the safety profile (readOnly=true, openWorldHint=true, idempotentHint=true, destructiveHint=false). The description adds behavioral context beyond that: which external services are consulted and their reliability ('Uses CrossRef (authoritative) and OpenAlex'), which informs how much an agent should trust the result. No contradiction with annotations.

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?

Four short sentences, each carrying distinct value: purpose, data sources, usage triggers, and parameter format. It is front-loaded with the core purpose and contains zero filler or repetition of information already in the schema or annotations.

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 single-parameter, read-only check tool with a present output schema and four rich annotations, the description covers purpose, sources, when-to-use, and parameter cardinality. The only gap is the undefined item_keys domain concept, which is minor given the schema and output schema handle the mechanics.

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 0%, so the description must compensate. 'Accepts one or more item keys' clarifies the otherwise ambiguous anyOf string-or-array schema and confirms batch multiplicity. However, it never defines what an item key is or where to obtain one, leaving part of the burden unmet.

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The description opens with a specific verb and resource: 'Check whether papers have been retracted or corrected.' It goes further by naming the data sources (CrossRef, OpenAlex), and the retraction-checking purpose is unique among the 40+ sibling tools, so an agent can distinguish it 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?

Provides explicit trigger conditions: 'when the user asks about paper validity, before citing papers, or as part of a literature audit.' These are concrete, actionable contexts. It lacks when-not-to-use guidance or named alternatives, but the stated triggers are clear enough to route an agent correctly.

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