evidence_group_delete_bulk

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description builds on that with a specific warning that permanently deleting sealed groups is unsafe due to issued reports. It adds a concrete restriction beyond the annotations though it does not elaborate on idempotency (already hinted) or partial-failure behavior. The warning about sealed reports is a meaningful extra context.

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 three purposeful sentences: it states the action, delivers a warning, and lists required inputs with a discovery pointer. It has no filler, front-loads the key distinction, and uses succinct imperative guidance ('never delete sealed groups') without redundancy.

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?

The description gives sufficient context for a destructive bulk operation: it covers purpose, scoping, warnings, and how to locate inputs. However, it omits the mandatory `requestId` from its explicit required-input list; though the schema defines it, an agent relying on the description could miss a required parameter. The absent output schema is not a problem for a delete operation, but the missing requirement in the prose is a small gap.

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?

With 67% schema description coverage, the description still maps 'evidenceGroupIds' to the `ids` parameter and explicitly references the search tool to find them. It also restates that caseFileId is required, but it fails to mention the required 'requestId' though that is fully defined in the schema. The description adds value for the otherwise undocumented `ids` parameter but doesn't fully cover all required parameters.

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 ('deletes') plus the resource ('SEVERAL evidence groups of one case file') in a single call. It distinguishes itself from the sibling evidence_group_discard (single group) and evidence_group_delete_bulk by explicitly contrasting with the singular alternative, so an agent can select it without opening schemas.

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 says 'prefer evidence_group_discard for a single group' and 'never delete sealed groups that back issued reports,' which provides clear when-to-use and when-not-to-use direction. It also tells the agent to use evidence_group_search to find the group IDs, closing the loop on how to prepare inputs.

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