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

With no annotations, the description carries the full load and does disclose real behavioral constraints: a pre-signature content restriction (no code, secrets, or confidential details), a post-signature verification obligation, and a mandated 'unknown' response with a statement of what a human must check. It stops short of saying whether answers are persisted, visible to counsel, or revisable, and says nothing about auth beyond the schema's matter_token note.

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?

Four tight sentences, front-loaded with identity and then the gating rule, then the verification rule, then the failure mode. No filler and every sentence carries a distinct constraint.

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?

No output schema and a nested answer object with evidence make this a complex call, and the description covers the decision rules and content limits an agent needs to produce a valid answer. It is slightly thin on the lifecycle of the answer after submission (terminal or editable, who sees it), which matters for a write-shaped tool with no annotations.

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 50%, so the baseline is 3; the description earns a point by giving operational meaning to the answer's source field — verify in code or running build and 'say how you know', otherwise use unknown — which tells the agent how to choose among the schema's enum values. The matter_id and question_id parameters are left entirely to the 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?

States a specific verb+resource ('Answer one of counsel's open questions') and identifies where those questions come from ('listed by get_matter'), so the agent can distinguish it from sibling tools like check_scope or feature_check without opening any schema.

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?

Gives explicit when-conditions split by workflow state: before the letter is signed only scoping questions may be answered (and those answers must be short and general), after signing answers must be verified in code or the running build. It also prescribes the fallback ('answer unknown') when verification is impossible.

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