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

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, so the agent knows this is a non-destructive, idempotent write. The description reinforces the mutation boundary ('does not upload or certify a file'), which is useful. However, it doesn't explain the 'unreviewed version description' status (missing_review) or why certifying is a separate step, which would be valuable context beyond 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?

Three tight sentences, front-loaded with the core purpose, then the negative scope, then the routing hint. No filler or repetition. Each sentence earns its place.

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 a 2-parameter, nested-object tool with no output schema, the description covers the core purpose and the two main scope boundaries. But it omits what the tool returns (the created record identifier, which is needed to call helvabase_link_evidence), and doesn't clarify the missing_review status semantics. Adequate but with clear gaps for a registration mutation.

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 50%. The critical idempotencyKey parameter is well documented in the schema itself ('never generate a new key to force a replay'), so the description needn't repeat it. But the nested 'evidence' object — which is the core payload — is undocumented in the description, leaving the agent to infer its structure (title, proofType, version, confidentiality, renewalLeadDays) from the schema alone.

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 the verb and resource: 'Register an evidence record.' It then adds a precise negative boundary — 'Does not upload or certify a file' — distinguishing it from a file-upload tool. Against siblings like helvabase_upload_original and helvabase_add_evidence_version, the boundary is helpful, but the description doesn't explicitly name those alternatives.

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 gives a clear next-step pointer: 'Use helvabase_link_evidence to propose a link from its exact version to a current requirement and supplier citation.' That is strong routing guidance for the downstream operation. It stops short of saying when to prefer helvabase_add_evidence_version over an embedded 'version' object, which is the main ambiguity given the nested version field.

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