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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so safety is largely covered. The description adds genuine context beyond them — deterministic behavior, version-binding, four dispositions with reason codes, and the explicit absence of a trust score — but it never explains why a pure assessment is not read-only (the schema's deprecated api_key field is the only place that hints the assessment is persisted to your account).

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?

Two dense sentences with no filler, and the core capability plus the output contract are front-loaded. The style is compressed to the point of being slightly cryptic, but every clause 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?

An output schema exists, so return values need not be described, and the description does cover determinism, version-binding, and the four-disposition contract. The remaining gap is behavioral: an agent cannot tell from the description what side effects justify readOnlyHint=false or what happens when a right is not documented — gaps that matter for a gating decision tool.

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 67% and the nested intended_use object is itself well documented, so the schema does most of the work. The description reinforces that the intended-use flags are rights the check must find documented and that the result is bound to a specific resource version, which adds a little meaning, but it gives no syntax, default, or geography/duration guidance beyond the schema.

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?

It states a specific verb and resource — a deterministic rights assessment of a resource against an intended use — and pins the scope to the exact resource version, license, and publisher authority. It differentiates itself from score-based siblings by declaring 'exactly four dispositions with reason codes; no trust score', but it never names the closest relatives (check_license, gate_check, check_rights_batch), so an agent must infer the boundary.

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?

There is no when-to-use guidance at all: no statement of when this should be preferred over check_license, gate_check, kya_check, or check_rights_batch, and no prerequisites such as having resolved a resource version or obtained a rights key. The binding language ('bound to the exact resource version') hints at a precondition but never states it as a rule.

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