create_contact

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

Annotations already declare idempotentHint=false, readOnlyHint=false and openWorldHint=true, so the safety profile is covered; the description goes beyond them with the non-obvious duplicate behavior and the conditional silent-skipping of phone/email when PHONE/EMAIL fields are absent. That silent failure mode is exactly the kind of side effect an agent cannot infer from structured fields.

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?

Front-loaded with the core action, then each subsequent sentence carries distinct load: idempotency caveat, prerequisite search, the conditional storage rule, the return value, and the sibling route. No sentence is redundant with another.

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 what is created, what is returned, when it silently drops data, and which sibling handles the combined case. Nothing an agent needs before invoking it is missing.

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 100% and the schema already documents all three parameters, so the baseline is 3. The description adds real semantics on top: email and phone are only persisted as WORK values when matching custom fields exist, which changes how the agent should treat a successful call with those arguments.

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?

States a precise verb and resource ('Create one contact') and immediately distinguishes itself from the tempting alternative by naming create_lead_complex and list_contacts. An agent knows exactly which tool this is versus its siblings without opening the schema.

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?

Explicitly tells the agent to run list_contacts first because the tool will not check for duplicates, and gives the condition for using the sibling instead ('To create a lead and contact together, use create_lead_complex'). Both when-to-use-this and when-to-use-something-else are covered.

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