verify_citations

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

With no annotations, the description carries the behavioral disclosure burden. It meaningfully discloses that the server automatically selects the strongest quote-verified evidence and that provided citations are treated as overrides, not additive suggestions. It does not mention side effects or mutation, but the audit framing plus the override semantics provide useful transparency.

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 compact and front-loaded with a one-line summary, followed by a normal-use instruction and the override caveat. Every sentence earns its place; there is no redundant repetition of schema information.

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 output schema exists and the parameter semantics are covered, the description provides enough for an agent to call the tool correctly in the normal case and to understand override behavior. It could add prerequisites or state whether this is read-only, but the core workflow is clear.

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: 'research_id only' clarifies the primary input, and 'optional citations are accepted only as explicit client overrides' adds real semantics to the citations parameter beyond the raw schema. The nested CitationCheck fields remain self-explanatory from their names.

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 labels the tool as a 'citation integrity + coverage audit' and clarifies that the server chooses evidence automatically, which distinguishes it from lower-level evidence tools like bind_evidence and judge_evidence. The verb+resource combination is reasonably clear, though 'Server-owned' is slightly jargon-heavy and the difference from sibling tools is implied rather than explicit.

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 explicitly states the normal call pattern ('pass research_id only') and explains when the optional citations parameter is appropriate ('only as explicit client overrides'). This gives clear context for the common case, though it does not name alternative tools or say when not to use this tool.

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