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

Beyond the readOnlyHint, idempotentHint, and destructiveHint annotations, the description discloses the important quirk that very old decisions may be returned hash-only and that the response explicitly says so. This is valuable behavioral context not available in any structured field.

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 focused sentences, each carrying distinct information: payload contents, old-record hash-only behavior, and REST equivalence. The main purpose is front-loaded and there is no filler or repetition.

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 read-only single-resource tool with no output schema, the description gives a complete picture of what the caller receives, including the edge case for old decisions. It also points to verification workflows, making the return content actionable.

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?

The schema describes api_key but leaves decision_id with only type and range constraints. The description implies that decision_id selects a stored decision, but it does not explicitly explain the parameter semantics or how the decision object relates to the ID. The description helps somewhat but does not fully compensate for the undocumented required parameter.

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 identifies the tool as retrieving one stored decision in full, including the decision object, the household version, and the evidence record. It differentiates from list_decisions by emphasizing 'one stored decision' and explicitly equating it to GET /api/v1/decisions/{id}.

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?

It establishes clear context: use when you need a single complete decision with evidence, and notes the exact REST equivalent. It does not explicitly contrast with siblings like list_decisions or narrate_decision, but the singular, full-payload framing gives adequate usage guidance.

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