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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered structurally. The description adds meaningful behavioral context beyond that: parameters are processed remotely without application persistence, sample labels are deduplicated, and outputs cover failures/exclusions/uncertainty. It also discloses non-capabilities such as no reputation ranking, identity verification, or Sybil detection. No contradiction with 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?

The core purpose and scope are front-loaded in the first sentence, with exclusions and usage pointers following. Nearly every sentence earns its place, though the negative list ('No public reputation ranking, identity verification, calibrated prediction or Sybil detection') partially overlaps with the earlier exclusion about not verifying reviewer identities. Minor redundancy keeps it from a 5.

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 tool with 5 required parameters, full schema coverage, and an output schema, the description covers the scope, intended review context, processing semantics, persistence behavior, and key limitations. The output schema presumably handles return-value details, so those need not be restated. The only minor gap is the ambiguous 'read its example resource' instruction, which could be more precise.

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?

The input schema has 100% description coverage with per-parameter descriptions, so the baseline is 3. The description reinforces the task/version/date-window framing that maps to 'task', 'version', 'asOf', and 'maxAgeDays', but it does not add type, format, or constraint details beyond the schema. It earns the baseline but not more, since the schema already carries the parameter semantics.

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 'reviews imported task outcomes' scoped to 'one task, version and date window,' and enumerates concrete behaviors such as deduplicating sample labels and showing failures, exclusions, and uncertainty. It also differentiates itself from evaluation and identity-verification tools with explicit negative scope. This goes well beyond the title 'Agent Evidence' and gives an agent a clear operational identity.

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 explicitly frames the intended use case ('helps review a supplier comparison') and states what it does not do: run evaluations or verify reviewer identities. It also directs the agent to 'fetch' or 'read its example resource' for exact inputs. It stops short of naming specific sibling alternatives for excluded use cases, so the when-not-to-use guidance is clear but not fully mapped to alternatives.

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