search

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

Annotations (readOnlyHint, idempotentHint, openWorldHint) already disclose safety and idempotency. Description adds beyond that: return type is 'mixed-type results in their native shape' and mentions scope-gating, which clarifies result shape and limitations.

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 sentences, no fluff. The key information (verb, resource, usage guidance) is front-loaded. Every sentence adds necessary context without redundancy.

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?

No output schema, but description explains return format ('mixed-type results in native shape') and mentions scope-gating. Missing details on pagination or error handling, but acceptable given tool complexity. Leaves agent informed about result shape and limitations.

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% with descriptions for all 5 parameters. Description adds value by providing concrete query syntax examples (e.g., 'type:ticket status:open'), which goes beyond schema descriptions. No contradictory info.

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 tool runs a Zendesk v2 Search query across tickets, users, organizations, and groups, returning mixed-type results. It distinguishes itself from siblings like list_tickets by emphasizing its cross-resource search capability.

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 advises to use this before list_tickets/list_users/list_organizations for specific records, calling out the search index as faster than enumeration. Also mentions scope-gating behavior, providing concrete when-to-use guidance.

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