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

The description adds substantial context beyond the annotations: null-clearing behavior for specific fields, the tenant-boundary restriction against moving contacts, the credential requirement, and the claimed-workspace precondition with a concrete 403 failure mode. These details are not expressed in the schema or annotations and directly affect whether an agent should attempt the call.

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 compact and front-loaded: it states the action, the required inputs, the clearing semantics, the tenant restriction, and then the auth/workspace prerequisites. No sentence is filler, and the ordering supports quick scanning.

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, idempotent mutation with no output schema, the description covers the critical behavioral surface: partial-update requirement, null-clearing fields, cross-customer restriction, credential requirement, and claimed-workspace gate with a 403 consequence. An agent has enough information to decide whether to call it and what to expect.

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 coverage is already 100%, so the baseline is 3. The description still adds two important constraints absent from the schema: at least one optional field must be supplied alongside contact_id, and null clears address in addition to phone and external_id (the schema description for address does not state this). These additions meaningfully improve parameter interpretation.

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 opens with a specific verb and resource: 'Change a contact.' It immediately distinguishes the operation from create/delete/update_customer by stating that contact_id is required and that a contact cannot be moved to another customer. An agent can identify this as a partial-update tool without consulting sibling 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 gives clear invocation conditions: pass contact_id and at least one mutable field, and note that null clears phone, address, or external_id. It also states when the tool will fail: moving to another customer is not allowed, and an unclaimed sandbox workspace gets a 403. The only gap is that it does not explicitly name sibling alternatives like create_contact or delete_contact.

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