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

Annotations already indicate it is not read-only, not destructive, and idempotent. The description adds the requirement for workspace-admin audit-log access and the implicit mutational nature of the operation. It also provides a security caution about treating field values as data, which is an important behavioral note beyond the 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?

The description is two sentences long, with the core purpose front-loaded. The second sentence adds a necessary security note. It is concise and each sentence earns its place, though it could be slightly more structured by separating the security note from usage guidance.

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 mutation tool with no output schema, the description covers the essential aspects: what it does, prerequisites (admin access, list_deleted_records), and a security caveat. It does not mention potential side effects beyond restoring, such as impact on related records, but given the existing dependency checks are referenced, it is fairly complete for an agent to call correctly.

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 only 25%, with only workspaceId having a description. The tool description does not elaborate on id, source, or idempotencyKey beyond what the schema provides (formats and min/max lengths). Since idempotencyKey is required but lacks a description, the description does not compensate for that gap, leaving potential ambiguity about its purpose.

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 ('Restore one recoverable CRM record'), specifies the resource (CRM record), and mentions the use of Anvil's existing dependency and retention checks, which distinguishes it from other record operations like create_record or delete_record. The mention of 'recoverable' and the pointer to list_deleted_records helps differentiate it from general record viewing or updating tools.

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 implicitly guides usage by requiring workspace-admin audit-log access and pointing to list_deleted_records to identify the record. It does not explicitly list when not to use this tool or compare with siblings like reopen_record or update_record, but the conditions for use are clear enough for an agent to decide when to call it.

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