search_connectors

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds the two behavioral facts annotations cannot express: the caller must supply an OAuth token, and results are paginated one page at a time. It stops short of describing result shape or pagination termination, so it is a genuine but not exhaustive addition.

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?

Purpose and scope lead, then exclusions, then the auth prerequisite — a sensible front-loaded order with almost no filler. The inline 'Google, Notion, and Slack' examples are compact and earn their place; the four short sentences are only marginally more than strictly needed.

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?

A six-parameter, paginated search with no output schema needs scope, auth, and pagination called out, and the description covers all three while ruling out the two confusable siblings. The remaining gap — what a returned connector record contains — is not required since no output schema exists, but a brief hint would have made it exhaustive.

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 description coverage is 100%, including per-parameter detail for query, pageSize, pageToken, connectorType, environmentId, and includeSetupStatus, so the schema already carries full semantic load. The description only adds the generic 'one page at a time' framing and adds no syntax or format detail beyond it; baseline 3 applies.

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?

Specific verb+resource: 'Search the connector catalog in one environment, one page at a time', with concrete examples (Google, Notion, Slack) that anchor what a connector is. It also distinguishes itself from the two nearest siblings, search_tools and list_connected_accounts, so an agent can route without opening any 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?

Explicit when-not guidance and named alternatives: 'Use search_tools to search actions on a connector' and 'This tool does not list connected accounts. Use list_connected_accounts for those.' Both boundaries an agent would otherwise guess at are stated outright.

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