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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds non-obvious behavior: 'Pending reads never resend provider requests' and a disclaimer that recommendations are not target executions, coverage guarantees, or calibrated probabilities. That is genuine semantic context beyond structured fields, though error/not-found behavior is unstated.

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 dense sentences, front-loaded with the core read action and scoping, no filler. Some phrasing is jargon-heavy ('handle', 'caller-authored') and could be plainer, but every sentence carries information.

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 exists, but the description compensates by characterizing what recommendations are and are not, and by noting that pending reads do not re-issue provider requests. Combined with read-only annotations and explicit project/environment scoping, an agent has enough to call it correctly and interpret the result.

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 only 25% (only operationKey is documented), so the description carries weight, and it does: it maps 'by ID' to recommendationId and the operation-key recovery path to operationKey, and adds the mutually-exclusive 'select exactly one handle' rule that the schema does not express (the schema permits both simultaneously). Pattern/min-length constraints remain schema-only.

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 ('Read one exact durable scenario recommendation') and names two retrieval modes (by ID, or by recovering the original operation key). It implicitly separates itself from the plural sibling firedrill_recommend_scenarios by emphasizing 'one exact' read, but never names an alternative tool, leaving that differentiation to inference.

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?

'Select exactly one handle' gives an invocation constraint, and the operationKey param description advises reusing the key after an uncertain response, which is real usage guidance. However, there is no explicit statement of when to prefer this tool over firedrill_recommend_scenarios or firedrill_scenarios, so alternatives remain implied rather than stated.

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