dossier_evidence_delete

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

Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds that the tool only works on DRAFT dossiers, which is useful context beyond annotations. It does not disclose additional behavioral traits like reversibility or permissions.

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 concise, consisting of two short sentences. The first sentence states the action and the second adds a condition and parameter list. It is front-loaded but the parameter list is somewhat redundant and slightly inaccurate.

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 destructive tool with no output schema, the description should provide more context about return behavior or success indicators. The parameter mismatch and lack of permissions or error conditions leave the agent underinformed. The DRAFT condition is helpful but insufficient.

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 lists parameters with incorrect names (e.g., 'evidenceId' instead of 'dossiEvidenceId') and omits 'dossiEvidenceGroupId'. This mismatch could mislead an agent about required inputs. The description adds minimal meaningful 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 clearly states the action 'Removes an evidence item from a dossier', which is specific and distinguishes from sibling tools like evidence_create and dossier_delete. However, the parameter names in the description (evidenceId) do not match the schema (dossiEvidenceId), causing minor confusion.

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 a clear condition: 'Only available while dossier is in DRAFT status'. It does not explicitly discuss when to use this tool versus alternatives, such as evidence_list or dossier_delete, but the condition helps narrow usage. No exclusions are given.

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