clients_bulk_delete

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

No annotations are provided, so the description carries the full burden. It meaningfully discloses the destructive behavior (deletion) and the conditional behavior around clients with existing documents ('skipped or cause an error depending on server configuration'). This is important behavioral context. However, it doesn't disclose whether deletion is reversible, what authorization/permissions are needed, or the response format/status codes that might result from partial failures.

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 two sentences and front-loaded, with the primary purpose and constraint stated first. The conditional behavioral note in the second sentence is important and earned. No wasted words, though the ambiguity in the second sentence ('skipped or cause an error') could be considered slightly more verbose than ideal.

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 batch mutation tool with a 100-item limit and conditional behavior around documents, the description covers the core mechanics but leaves gaps: it doesn't clarify the outcome for the ambiguous 'skipped or cause an error' condition (which is configuration-dependent), doesn't state whether the operation is atomic or partial-commit, and doesn't describe what happens with invalid UUIDs mixed into a valid batch. No output schema exists to fill these gaps.

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 100%, so the schema already documents both parameters (ids as UUID array max 100, companyId as optional override). The description adds the UUID requirement to the description text but largely repeats what the schema covers. It doesn't add meaning about id format validation, how errors map to specific ids, or behavior when some ids are invalid while others are valid.

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 ('Delete multiple clients in a single request') with a specific verb and resource. It adds useful scope details (up to 100 UUIDs) that distinguish it from the single-delete sibling clients_delete. However, it doesn't explicitly name the alternative (clients_delete) or the related suppliers_bulk_delete sibling, though the bulk nature is clear from the name and description.

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 implies batch usage ('multiple clients in a single request') and the 100-UUID constraint provides some usage framing, but it gives no explicit when-to-use guidance versus clients_delete, and doesn't state when bulk delete is preferred over individual deletes. There's no exclusion guidance or mention of company context requirements beyond the schema field.

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