evidence_seal

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

The description adds significant behavioral context beyond annotations: explains async behavior ('triggers async timestamping'), state transitions ('OPEN → CLOSING → CLOSED'), and immediate return. Annotations indicate destructiveHint=true and readOnlyHint=false, which aligns with 'closes the group.' No contradiction.

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 sentences cover purpose, effect, and post-usage instruction. Every sentence adds value, no waste. Front-loaded with the primary action.

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 high complexity (13 parameters, nested objects, no output schema), the description fails to explain parameter semantics, which is essential. The agent cannot determine what 'id', 'caseFileId', 'evidencesCount', and other fields represent. Purpose and process are clear, but parameter understanding is deficient.

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%, and the description provides no explanation of any parameters. For a tool with 13 parameters (3 required), this is a critical omission. The agent receives no guidance on what each parameter means or how to use them.

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 uses specific verbs 'seal and certify' with a clear resource 'evidence group'. It distinguishes from sibling tools like evidence_group_create (create) and evidence_group_list (list) by focusing on the closing and certification action.

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 description provides clear workflow context: 'Poll evidence_group_list until status is CLOSED before linking to a dossier.' It implies when to use (to seal) and when not (if evidence still needs to be added). However, it lacks explicit exclusions compared to alternatives.

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