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

Annotations declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the write-vs-read profile is already covered. The description adds genuinely new context: the API-key authentication requirement, the per-side/per-stage invocation limit, and the evidenceId citation convention. It omits the idempotencyKey retry behavior that the schema documents, and says nothing about what happens to the stage after the statement is made.

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?

Three dense sentences, front-loaded with the core action, then the stage taxonomy, then the constraints. No filler, though the stage-type enumeration is slightly list-heavy relative to the rest.

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?

For a mutation tool with no output schema, the description covers auth, eligibility, and the stage-dependent nature of the statement. The main gap is that it doesn't hint at the outcome (whether the stage advances or what the server returns), which an agent calling a state-changing tool would benefit from knowing.

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 100%, so every parameter (text, caseId, evidenceIds, idempotencyKey) is already documented in the schema. The description's only added meaning is the 'cite evidence by evidenceId' convention, which is marginal over the schema. Baseline 3 applies.

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?

Specific verb+resource ('Speak for your side in the current stage') with an explicit enumeration of what a stage can be (OPENING_*, EVIDENCE_*, ANSWERS, CLOSING_*). This clearly separates it from siblings like submit_evidence, respond_to_complaint, and conclude_stage.

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?

Usage is tied to the stage type, which is a clear trigger condition, and the constraint 'one statement per side per stage, made by the side's representative' tells the agent when the call is valid. It never explicitly names a sibling to use instead (e.g., submit_evidence for adding new evidence), so it stops short of full when/when-not guidance.

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