get_citations

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

With no annotations, the description bears full responsibility for behavioral disclosure. It mentions supported formats but fails to describe what happens if the session is invalid, whether it's a read-only operation, or the output structure. The lack of side-effect or error information leaves significant 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 two concise sentences. The first states the purpose, the second lists supported formats. No unnecessary words or repetition, and it is front-loaded with the core function.

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 tool is relatively simple, but the description omits details about the dependency on an existing research session and the exact behavior of the output (beyond 'citations'). With no output schema, more return-value context would be helpful. However, the core function is covered.

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 does help by listing the three formats, which map exactly to the enum values for the 'format' parameter. It also provides context for 'sessionId' by referencing 'research session', but does not elaborate on what constitutes a valid session or the required nature of the ID.

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 the tool's function: getting formatted citations from a research session, with specific format options. This is a specific verb+resource+context that distinguishes it from sibling search tools.

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 phrase 'from a research session' implies it should be used when you have an existing session, but there is no explicit guidance on when to use it versus alternatives like add_source or research_session. No when-not-to-use or alternative tools are mentioned.

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