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

Annotations only say readOnly=false, idempotent=false, destructive=false; the description goes well beyond by disclosing that value creates a proposal requiring approver/owner sign-off before any write, that confirm suppresses future re-asks of the same check, and that stale-household calls are refused. It also names the equivalent REST route for cross-checking semantics.

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 value/confirm distinction is front-loaded and every clause carries information, but the sentences run long and the role and refusal clauses are crammed in as fragments rather than structured bullets, making it slightly harder to scan than necessary.

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?

With no output schema, the agent must infer return shape, and the description doesn't say what comes back after a value proposal versus a confirm. Apart from that and the unexplained note/api_key parameters, the behavioral picture for this 5-parameter mutation tool is essentially complete.

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 only 20%, so the description carries real weight and does explain value and confirm well. But note and api_key receive no semantic explanation (the phrase 'Developer, approver or owner key' only vaguely gestures at api_key), and question_id is only implied, leaving a third of the 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?

States a specific verb and resource ('Answer one open question') and immediately enumerates the two mutually exclusive answer modes, so the agent knows exactly what the call does. It also distinguishes itself from read-only siblings like list_questions by making clear this records or proposes a resolution.

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?

Explicitly says 'Send exactly one of them' for value vs confirm and explains the divergent consequences of each ('must approve before anything is written' vs 'records that the data is right'). It also gives the refusal condition ('household changed since the question was asked') and the required role, which is precisely the when/when-not guidance a caller needs.

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