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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful domain behavior: status filtering semantics, the rule that citing unaccepted evidence fails rules, and the 'Free to call' cost signal. It doesn't describe pagination or result ordering, keeping it from a 5, but it goes well beyond the annotations.

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 sentences are front-loaded with the return contents and then the status filter semantics. Every sentence adds value, though the second sentence is dense and could be split for readability. No wasted 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 2-parameter read tool with no output schema, the description supplies the necessary behavioral context: status filtering semantics, default behavior, and the evidence-acceptance rule. It omits pagination/ordering and workspaceId fallback context, which are minor gaps given annotations cover safety and the schema documents workspaceId.

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 50% and the status enum is defined in the schema, but the description adds real meaning: status omission defaults to returning everything, and the three enum values are contextualized with what each means for downstream rule checks. workspaceId is not described beyond the schema, but the main semantic parameter is well covered.

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 clearly states a specific verb (list) and resource (evidence bank) and enumerates the returned fields (id, kind, text, source, adder, status, acceptance time). It doesn't explicitly contrast with a sibling tool, but the returned-field enumeration and 'evidence bank' scope make the tool's unique role clear enough that an agent can identify it.

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?

Usage is implied by the status semantics: omitting status returns everything, and accepted vs pending vs rejected meanings are explained. However, there is no explicit when-to-use vs alternative guidance, and no statement of when NOT to use it (e.g., for a single evidence item). The guidance is adequate but not comparative.

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