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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds meaningful behavioral context: it checks against four databases, issues verdicts (verified, mismatch, not_found, unverifiable), flags retractions and corrections, and can output corrected BibTeX. This goes beyond the annotations and explains the tool's behavior in detail.

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?

The description is a single, efficient sentence that front-loads the core action ('Checks up to 30 citations') and then packs in the key details (sources, verdicts, flags, and the optional BibTeX output). Every phrase earns its place with no fluff or redundancy.

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?

The description covers input formats, limits, sources, verdict types, and the optional corrected BibTeX. Since an output schema exists, return values are presumably documented elsewhere. The only minor gap is that it doesn't explicitly mention what happens if the input exceeds 30 citations, but 'up to 30' implies a limit. Overall, it is well-rounded and sufficient for an agent to call it correctly.

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?

The input schema describes both parameters, but the description adds value by specifying that 'text' can be a pasted reference list, one per line, numbered, or BibTeX. It also clarifies that 'bibtex=true' adds corrected BibTeX per reference, which is consistent with the schema. This enriches the parameter semantics beyond the schema alone.

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 clearly states a specific verb ('Checks') and a specific resource ('up to 30 citations'), and details the sources and verdict types. It distinguishes itself from siblings by the scope (list vs. single work, and covering multiple sources vs. retractions) even though it doesn't name them explicitly. A minor deduction for not directly naming the alternatives.

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?

The description implies usage (verifying a reference list) and provides a clear limit (up to 30) and input formats, but it does not explicitly state when to choose this over check_retractions or lookup_work, nor does it mention exclusions or prerequisites. The context is clear but no explicit guidance is given.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about being fast and using specific data sources, and mentions 'not_in_crossref' as a possible status, which hints at behavior for unknown DOIs. This adds some value but does not deeply describe side effects or limitations beyond the 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?

The description is two sentences with no fluff. The first sentence states the purpose, limits, and data sources; the second lists possible statuses. Every word earns its place, and critical information is front-loaded.

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?

Given the low complexity (one parameter, batch operation), the existence of an output schema (which presumably details return structure), and annotations covering safety, the description is complete. It provides all necessary context: what is checked, limits, data sources, and possible statuses. No critical information for correct invocation is missing.

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 0%, so the description must compensate. It clearly explains the single parameter (dois) is an array of DOIs to be batch-checked, up to 200. This adds meaning beyond the schema's structural constraints, even though it doesn't detail DOI format beyond length.

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 uses a specific verb ('check') and resource ('DOIs'), and clearly enumerates the statuses returned. It distinguishes itself from siblings by focusing on retractions, partial retractions, expressions of concern, and corrections, while check_references and lookup_work serve different purposes.

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 provides explicit context: batch operation, up to 200 DOIs, and data sources (Crossref and Retraction Watch). However, it does not explicitly mention when to use this tool over check_references or lookup_work, nor does it state when not to use it. The guidance is clear enough for a straightforward batch check.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful context by listing specific record components such as retraction and correction notices and a newer published version, which is valuable beyond the annotation metadata. No contradictions exist.

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?

The description is a single sentence that front-loads the core action and then enumerates inputs and outputs economically. The list of returned fields makes the sentence longer but each item adds useful detail. No redundant filler is present.

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 one-parameter lookup tool with rich annotations and an output schema, the description provides enough operational context to invoke the tool correctly. It covers accepted input formats and the nature of the returned record advances. It does not discuss error cases or ambiguity handling, but these are less critical given the simple parameter surface.

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?

The single parameter 'id' has 100% schema description coverage, listing DOI, arXiv id, PMID, URL, title, or citation. The tool description essentially repeats the same accepted input forms, adding little meaning beyond the schema. With full schema coverage, the baseline of 3 is appropriate.

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 states a specific verb ('Returns the record') and a concrete resource ('one work'), and enumerates both accepted inputs and returned fields. It clearly identifies the tool's scope as a single-record lookup, setting it apart from the sibling check tools that validate references or retractions.

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?

The description implies usage when a record for a DOI, arXiv id, PMID, or citation is needed, but it provides no explicit guidance on when to use this tool instead of check_references or check_retractions. It does not state any exclusions, prerequisites, or alternative routing conditions.

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