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

Goes well beyond annotations: discloses the required action scope for auth, that credits are reserved (prepaid maximum from the quote), that an operation_id is returned and must be polled via get_operation, and that sandbox execution is simulated. Annotations (openWorld, idempotent, non-destructive) only cover the safety profile, so this added operational context is genuinely valuable.

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?

Front-loaded with the core action and prerequisite, and nearly every clause carries information. The dense semicolon-chained clauses make it slightly run-on rather than crisp, keeping it just under the top mark.

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?

With no output schema, the description compensates by naming the returned fields (evidence_id, SHA-256 hash, timestamped metadata, operation_id) and the polling tool. Auth, credit reservation, and sandbox behavior round out everything needed to invoke it correctly.

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 100%, so the baseline is 3 and the schema already carries both parameter definitions. The description adds surrounding meaning by explaining where quote_id originates (create_quote with action='evidence' and the full task input) and the async result flow, though it says nothing extra about idempotency_key beyond what the schema documents.

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+resource ('Capture a new immutable metadata observation') scoped to 'an existing case', and clearly distinguishes itself from siblings by naming create_quote as the prerequisite and get_evidence as the export path. An agent can tell what this does versus its neighbors without opening any schema.

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?

Explicit ordered workflow: call create_quote with action='evidence' and a defined input object first, then capture, then use get_evidence to export. It also names what this tool does NOT capture (screenshots, images, audio, video), which prevents misuse. Conditions selecting this tool versus alternatives are fully specified.

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