Contest Verdict

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

The description thoroughly discloses behavioral traits beyond annotations: it describes the meta stamping (timestamp, reason, original_outcome, new_session_id), the creation of a new session with back-link, chain-of-custody invariant, and preconditions (final state, no double contestation). Even without annotations providing safety hints, the description conveys the tool's behavior comprehensively.

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 front-loaded with the main action and provides necessary details about preconditions and effects. It is somewhat long but structured logically. Every sentence adds value, though some technical jargon (e.g., 'chain-of-custody append-only') may be dense.

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 (creates new session, modifies state, has invariants) and the absence of an output schema, the description covers behavioral aspects well but omits parameter details for 4 parameters. It also does not describe the return value or the new session's initialized fields. This is a moderate completeness gap.

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%, so the description should document parameter meanings. It indirectly covers session_id, reason, and new_task, but fails to explain caller, new_caller, response_format, and new_initial_draft. The description's parameter guidance is incomplete, leaving 4 out of 7 parameters undocumented.

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 purpose: 'formally contest a final verdict and open a new deliberation cycle.' It explains the two possible caller states and how the tool fits into the cross-review model. It also distinguishes itself from sibling tools like session_finalize by describing the contestation workflow.

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 provides explicit usage guidance: the agent should use this tool when the caller is NOT_READY, and only after the original session is in a final state (converged/aborted/max-rounds). It also warns against contesting an in-flight session or a session that has already been contested. However, it does not explicitly contrast with sibling tools like escalate_to_operator or session_doctor.

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