Save answers before the scan has facts

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

Adds substantial context beyond the annotations: answers persist on the project and are applied at fact-read time, conflicting document values surface as a conflict, late calls are refused, tier is not recomputed, and assessments:write is required. It never says whether prior answers are overwritten, which matters given destructiveHint=true.

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, each adding a distinct constraint (timing, persistence, conflict behavior, permission), with the timing rule front-loaded. No filler or restatement of the title.

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?

Lifecycle, failure mode, and auth are well covered for a mutation tool, but with 0% schema description coverage and no output schema the agent gets no guidance on constructing the answers payload, which is the core input.

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 carries the burden, yet it says nothing about how the answers array is shaped — no mention of factPath, the boolean/string-array/null value union, or justification. 'Checklist answers' is the only hint about the required payload.

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 and resource ('Save the checklist answers') and pins the lifecycle position ('right after air_start_assessment'). It doesn't explicitly contrast with the similarly-named sibling air_submit_fact_answers, so the agent must infer the distinction.

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 a clear entry condition (call immediately after air_start_assessment) and an explicit exclusion ('Refused once the scan has read its facts'). It stops short of naming an alternative tool for answering after facts are read.

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