Create a contact

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

Annotations declare non-readOnly, non-idempotent, non-destructive, and open-world. The description enhances this by detailing the lack of duplicate detection, the never auto-retry policy, the eventual consistency for search indexing, and the photo limitation. These behavioral details go beyond what annotations convey and help the agent anticipate side effects.

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 dense but every sentence carries operational value. It is front-loaded with the purpose and return object, then systematically covers required fields, failure handling, indexing delay, and photos. Slightly long but not padded; could be trimmed without loss, but structure is sound.

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 tool with 14 parameters (nested objects) and no output schema, the description covers all essential operational aspects: return values, required-field rule, duplicate risk, failure strategy, indexing behavior, and photo limitation. It fully equips an agent to call correctly and handle edge cases.

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%, so the baseline is 3. The description adds meaningful constraints not in the schema: 'at least one is required' and the default person_fields mask, plus the clarification that an absent field may be unmasked. This goes beyond simple restatement.

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 'Creates a new contact in the account's Google Contacts and returns the created Person' — a specific verb and resource, clearly distinguishing it from update_contact, list_contacts, and sibling tools. It names the return object and its fields, leaving no ambiguity about the tool's intent.

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 explicit when-to-use guidance: states the requirement of at least one field, warns against auto-retry on ambiguous failures, instructs to verify via search/list before re-sending, and notes the indexing delay for search_contacts. It also names the photo-related alternative (raw_request with updateContactPhoto), providing clear routing among siblings.

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