Create contact

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

Annotations already signal a write operation (readOnlyHint=false), open-world side effects (openWorldHint=true), and non-idempotency (idempotentHint=false). The description adds genuine context beyond this: the matching/deduplication behavior for email/phone and the fact that the created contact is returned. It doesn't disclose potential side effects like workflow triggers, but the annotations cover openness. No contradiction found.

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?

Three terse sentences with no filler: purpose, the key correctness constraint, and the return value. Front-loaded and every sentence earns its place, especially valuable since there is no output schema to document the return.

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 9-parameter, 0-required create tool with no output schema, the description covers the core behavioral points (dedup matching, return value) but leaves the undocumented params unsupported and says nothing about side effects beyond what annotations imply. Adequate for the main path, with clear gaps for 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?

With schema coverage at 56%, the description's dedup note adds real meaning for email and phone, which the schema only partially documents (email has no description, phone just a format hint). However, firstName, lastName, and companyName remain undocumented in both the schema and the description, so the description only partially compensates for the coverage gap.

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 'Create a new contact,' a specific verb and resource that clearly differentiates this tool from siblings like ghl_get_contact, ghl_update_contact, and ghl_search_contacts. The added dedup context and return-value statement sharpen the purpose. It doesn't explicitly name sibling alternatives, so it stops short of a 5.

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 dedup recommendation ('At least one of email or phone is recommended so the contact can be matched/deduplicated') gives actionable guidance on how to invoke the tool effectively. However, it never states when to choose create over update/get/search, nor does it mention any exclusions or prerequisites. Usage context is implied rather than explicit.

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