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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with concrete consequence language ('files nothing and stores nothing'), which is more actionable than the hint alone. It also discloses a non-obvious behavioral trait — that providing flightNumber plus flightDate triggers an internal flight lookup when route or delay is missing — and states what the return contains. It doesn't cover failure modes or how confident or approximate the estimate is.

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 sentences, front-loaded with the core purpose and ending with the return shape and safety profile. Dense but not padded; the jurisdiction list is long yet each item carries information. A slightly tighter phrasing of the closing sentence would earn a 5.

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 an 11-parameter tool with no output schema, the description still explains what comes back (verdict, estimate, explanation), what inputs drive it, the fallback lookup path, and the read-only guarantee. An agent can call this correctly without opening anything else.

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 100%, so the baseline would be 3, but the description adds domain meaning by naming the actual decision inputs — route distance, delay at the final destination, notice given, operating airline and the time limit — which tells the agent why delayBand, cancelNotice, airlineIata and flightDate matter. That is real value beyond the field-level descriptions.

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 ('preliminary check of whether ... is likely to be owed fixed compensation'), names the four jurisdictions covered, and enumerates the disruption types handled. It is clearly distinguishable from the siblings look_up_flight and get_claim_link because it produces a verdict and estimate rather than a lookup or a filing link.

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?

The word 'preliminary' plus 'Read-only: files nothing and stores nothing' makes the intended position in the workflow clear: assess eligibility before doing anything else. It stops short of naming get_claim_link as the follow-on tool or stating explicit exclusions, so it is clear context rather than a full when/when-not/alternatives statement.

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