integrations_test

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

Goes beyond the destructiveHint=true annotation by partitioning the tool's behavior: inspect has no side effects, while run performs real writes (event create/update/delete, sheet writes, Airtable creates) that require user confirmation. That is meaningful disclosure of what actually gets mutated, though return-size behavior via mode and auth/prerequisite requirements are not covered.

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?

Core behavior is front-loaded and the safety warning is well placed, but the closing 'Actions: inspect — … | run — …' sentence restates what the first two sentences already said, adding bulk without new information.

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?

With no output schema, the description does the necessary work of saying what each action yields: inspect returns the names, descriptions and params the agent sees, run returns the tool's output or error. Enough for a 7-param, side-effecting tool, with only permission/prerequisite context and mode's effect on results left implicit.

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?

The schema leaves `action` and `agentId` undescribed, and the description compensates by defining inspect vs run and their required context. It also explains `toolName` as the tool from inspect output and `args` as matching inspect's parameters, adding relational meaning the schema doesn't convey; mode and orgId are left to the schema.

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 specific verb+resource: testing an agent's integration tools against its real runtime code and settings, and splits that into inspect vs run with distinct semantics. It doesn't differentiate itself from the sibling test_agent_tool / test_agent_tool_request tools, so an agent can't tell from this description alone which testing tool to reach for.

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-to-use: inspect to debug why an agent misuses a tool, run to reproduce the agent's exact call, plus a concrete list of safe read-only checks to start with and an instruction to confirm destructive operations with the user first. It gives no guidance on choosing between this and the sibling test_agent_tool tools.

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