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

Beyond the annotations, it discloses that the record goes to a public signed log, that no name/number/address of the checked party is stored, that re-calling yields the identical reference, and that verification does not require trusting AstraNL. These are exactly the behavioral traits an agent cannot infer from readOnlyHint=false / idempotentHint=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?

Three dense sentences, front-loaded with the purpose and outcome. Every clause carries distinct information: purpose, trust model, eligibility window, privacy guarantee, idempotency. No filler.

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 single-parameter write tool with no output schema, the description covers the return value ('a reference'), the downstream consumer, the freshness constraint, privacy implications, and idempotency. Nothing an agent needs to invoke it correctly is missing.

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% and check_id's format is fully documented there, so the baseline is 3. The description adds a semantic constraint on the referenced check (must be produced within 48 hours) that meaningfully qualifies valid inputs, lifting it slightly.

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 states a specific verb+resource ('records its digest in the AstraNL signed public log') and defines the concrete outcome ('returns a reference that a colleague, approver or auditor can check later'). It clearly distinguishes itself from sibling check_counterparty_nl (the producer of the input) and verify_astranl (the later consumer).

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 explicitly names the alternative tool (verify_astranl), the audience that consumes the record (colleague, approver, auditor), and a hard eligibility window ('works only for a check AstraNL produced in the last 48 hours'). It stops short of stating an explicit when-not-to-use case beyond that window, so not quite a 5.

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