record_statement

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 clearly states mandatory extraction fields (record time, investigators, location, AV-recording flag, content) and the hard requirement that full_text be a verbatim transcript, marking summary-only registration as incomplete. This is substantial behavioral context, though it stops short of describing response behavior or side effects.

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 dense and well-structured: a one-sentence purpose, a requirements sentence, and a compact parameter block. Every sentence carries necessary information with no filler. Slightly long, but justified by the number of required fields and the verbatim rule.

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 tool's complexity (13 required parameters, no annotations, no visible output schema details), the description provides the core operational requirements, parameter list, and a critical completion criterion. It does not mention invocation mechanics (case_id/args nesting) or error conditions, but those are partly covered by the input schema, so the description is largely complete for an agent to invoke 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?

Schema coverage is 0%, but the description compensates by listing all 13 args fields with required flags, including the role enum values and explanations for person and role. It lacks explicit types or formats (e.g., date format for record_time, boolean for has_av_recording, meaning of occasion), but is far richer than the near-empty input schema.

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 opens with '登记供述/辩解或证言' (record statements/defenses or testimony), naming a specific verb and resource. It further distinguishes itself from siblings by enumerating roles (defendant/codefendant/witness) and requiring verbatim Q&A transcription, which clearly separates it from record_party, record_indictment, and record_documentary_evidence.

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 when to use the tool (whenever a statement, defense, or testimony must be registered) and emphasizes that full_text must contain verbatim Q&A, with summary-only entries considered incomplete. However, it does not explicitly mention alternatives or exclusions, leaving the agent to infer the boundary versus sibling recording tools.

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