check_citations

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

No annotations are provided, so the description carries the full burden of disclosing behavioral traits. It does state the tool checks existence and metadata completeness, which is useful. However, it does not clarify whether the operation is read-only, whether it has side effects, whether it requires network access, or what happens when metadata is incomplete. This is a modest disclosure but leaves notable gaps.

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 exactly two sentences, front-loaded with the main action and then the specific detail. Every sentence earns its place, and there is no redundancy or filler.

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 the core functionality (DOI existence and metadata validation) but omits mention of the 'suggest_enrichment' feature, which is a distinguishing capability of the tool given the parameter exists. With an output schema present, return values are covered, but the high-level description leaves out a notable feature, making it incomplete for a user trying to understand the tool's full purpose.

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 fully describes all three parameters with 100% coverage, so the baseline is 3. The description adds no additional meaning beyond the schema; it does not explain how 'validate_metadata' or 'suggest_enrichment' behave beyond their schema descriptions, nor does it relate them to the description's mention of 'metadata completeness'.

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 identifies a specific verb ('check') and resource ('citations against the local CrossRef database'), and explains the two main actions (validate DOIs exist, check metadata completeness). It is more specific than a tautology and distinguishes from sibling tools like search_by_doi (which finds DOIs) and enrich_dois (which improves metadata). However, it could more explicitly differentiate from check_bibtex, so not a perfect 5.

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 the tool is used to validate DOIs against a local database, but it provides no explicit guidance on when to use it versus alternatives such as search_by_doi, check_bibtex, or enrich_dois. Since sibling tools are listed in context, the description misses an opportunity to state exclusions or preferred scenarios.

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