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

With no annotations, the description carries the full burden and does so well: it discloses redundancy ('two protected locations'), the meaning and limits of the receipt ('does not certify that a claim is true'), availability dependence on configuration, credential requirement ('key'), and explicit cost/rate constraints ('No agent fee in this release; 1 MB per package, 200 upload attempts a day'). This is rich, non-obvious behavioral context.

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?

The core facts are front-loaded, but the text is padded with first-person framing ('I want to preserve...') and a label-value tail ('Credential: key. Cost: ...') that reads like boilerplate. Several strong points sit in an undifferentiated block rather than being prioritized.

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 complex nested-input, no-annotation tool with no output schema, the description adequately covers behavior but leaves the parameters essentially undocumented and only gestures at the return ('issues a signed receipt'). An agent still lacks enough to correctly construct requestId, attestations, or the full bundle.

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 0% across four parameters, so the description must compensate. It loosely maps intent to 'consentToStore' ('with your explicit consent') and to bundle contents ('instructions, work and delivery records'), but does not explain requestId, attestations, happenedAt, reference, or the bundle's structural requirements. Partial compensation 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?

The description states a specific verb and resource: it 'keeps a private evidence package in two protected locations and issues a signed receipt.' This is more than a restatement of the name. However, it does not name or contrast with likely siblings such as hold_record, file_claim, register_anchors, or notarise, so sibling differentiation remains implicit.

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 conveys a key precondition ('With your explicit consent') and clarifies scope against adjacent capabilities ('Timestamp stamping through public calendars follows separately'), but never states when to choose this tool over alternatives or when not to use it. Usage is largely left to inference.

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