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

With no annotations, the description partially carries the behavioral burden by disclosing that this is an 'append-only event' and that it folds into missing/received/superseded states. However, it does not explain failure modes, permissions, idempotency, or what happens when evidence is declared for a non-existent or already-completed run.

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 description is short and the main purpose is front-loaded in the first sentence. The second sentence is dense but informative, though the phrase 'folded with received attachments' is somewhat compressed and may require domain knowledge to parse.

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?

Given the moderate complexity, full schema coverage, and presence of an output schema, the description covers the core operation but leaves usage guidance and the meaning of the folding behavior implicit. An agent could call it correctly, but not with full confidence about when it should be chosen over evidence_attach.

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 schema already documents all six parameters and their meanings. The description adds no parameter-level detail beyond what the schema provides, so the baseline score of 3 is appropriate.

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?

Uses a specific verb and resource: 'Declare required evidence on a Process run' immediately identifies the operation and target. The phrase 'append-only event' plus the contrast with sibling tools like evidence_attach and evidence_get makes its role in the evidence lifecycle clear.

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 intent is implied by the action word 'Declare' and by the sibling context, but the description never explicitly says when to use this tool instead of evidence_attach or evidence_get. No exclusions or alternative selection criteria are given, so an agent must infer the boundary between requiring evidence and attaching evidence.

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