get_citations

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that the tool collects a citation graph from three sources; it does not mention pagination, rate limits, error handling, or what happens when an identifier is invalid. There is no indication of whether the result includes full citation details or just counts, and no mention of authentication requirements. This is a significant gap for a cross-source aggregating tool.

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, front-loaded sentence with no fluff or repetition. It efficiently conveys the core purpose and the involved sources. It is concise but not over-minimal – it earns its place. A 5 would require slightly more detail about the return behavior without adding length.

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 complexity of aggregating three sources, the lack of annotations, and no output schema, the description is incomplete. It does not explain the response structure, how limit interacts with the graph, or any edge cases. An agent would need to either infer behavior from the schema (which has no descriptions) or risk making incorrect assumptions. More context is necessary for correct invocation.

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 by explaining the parameters. It does not. The identifier is implied by the phrase 'one paper', but the limit parameter is completely unexplained – what does it limit? Number of citations per source, total results, or something else? No additional meaning is provided, leaving the agent to guess.

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 ('Collect') and a specific resource ('cross-source citation graph') for one paper, and names the three sources (Scopus, OpenAlex, Semantic Scholar). It clearly distinguishes itself from sibling tools like get_paper or search_* by specifying the multi-source citation gathering intent. However, it leaves 'citation graph' somewhat vague (does it return citing papers, counts, or metadata?), so it's not a 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 does not provide any explicit when-to-use guidance, nor does it mention alternatives or exclusions. It implies usage for collecting citations across the named sources, but there is no instruction on when to prefer this over get_paper or search_* tools. An agent would have to infer the use case from the tool name and brief description.

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