Contest Verdict

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

Annotations only indicate not read-only, not destructive, not idempotent. The description goes far beyond: it details side effects (stamps a contestation record, initializes a new session, links via contests_session_id), auth requirements (capability token or operator token), and error conditions (cannot_contest_in_flight_session). This is thorough disclosure of behavioral traits, fully compensating for the sparse annotations.

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 but every sentence adds critical information: purpose, constraints, auth, conditional logic, side effects, preconditions, and invariants. It is front-loaded with the core purpose and follows a logical flow, making it efficient without redundancy.

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 (7 params, 3 required, no output schema, rich invariants), the description covers all essential aspects: prerequisites, side effects on the original and new sessions, chain-of-custody rules, and error cases. There is no mention of return value, but without an output schema and given the action-oriented nature, this is acceptable; the agent has enough to call it 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 description coverage is 0%, so the description must compensate. It explains the primary parameters—session_id (the contested session), reason (max 4000 chars, though this repeats schema), and new_task (implied as the task for the new session)—and mentions new_initial_draft implicitly by context. However, it does not explain new_caller, response_format, or caller, leaving those to inference from defaults and enums. Partial compensation, but gaps remain.

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 'formally contest a final verdict and open a new deliberation cycle,' a specific verb and resource that clearly distinguishes it from siblings like session_finalize or session_init. It unambiguously states the tool's function and scope, making its purpose immediately understandable.

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?

Provides explicit conditions: 'Petitioner READY (acata) → notify the human operator ...; petitioner NOT_READY (contesta) → contest_verdict.' It also states preconditions ('original session must be in a final state') and exclusions ('once contested, a session cannot be contested again'), and instructs to 'contest the LATEST session in the chain.' This gives clear when-to-use and when-not-to-use guidance relative to alternatives.

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