update_contact

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It mentions PATCH, implying a partial update, but does not explain what happens if the contact is not found, how email ambiguity is resolved, or how the `properties` object merges with existing custom properties. It also omits idempotency, error handling, and response shape, leaving critical behavior undisclosed.

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 extremely concise: two sentences, front-loaded with the primary purpose and the critical email/domain rule. Every word earns its place, with no redundancy or filler. The structure makes it easy to scan and extract the key information.

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 and no annotations, the description is incomplete. It does not mention what the response contains, error scenarios (e.g., invalid id, ambiguous email), or whether the update is partial (only provided fields). It also fails to clarify that `properties` refers to custom contact properties, which could lead to misuse. Given the tool's complexity (6 parameters, nested object), the description leaves too much to inference.

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?

The description adds meaningful context for `id` (can be an email) and `domain` (disambiguates email across pools), which directly aids correct usage. Schema descriptions already cover these two parameters. For the remaining parameters (last_name, first_name, properties, unsubscribed), the names are self-explanatory but the description does not elaborate on their semantics or update behavior. Given the 50% schema coverage, the description partially compensates but leaves gaps for the undocumented 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 clearly states the action (Update), the resource (a contact), and the addressing methods (id or email). It also specifies the HTTP method (PATCH) and implicitly differentiates from sibling tools like get_contact and delete_contact by focusing on the update operation. The mention of 'picks the pool' for email adds specificity.

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 gives a direct usage rule: pass `domain` when addressing by email, which is essential for correct invocation. However, it does not explicitly compare this tool to alternatives like update_contact_property or explain when to prefer this over other contact-related tools. The guidance is clear for the addressing method but lacks broader selection criteria.

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