Integration call

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

Adds real context beyond the annotations: results and errors pass through unchanged, refused names point back to search, and permissions match a direct invocation — which importantly explains that destructiveHint is inherited from the target tool rather than universal. What's missing is any note on side effects like rate limits, retries, or whether arguments are validated against the target schema.

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?

Front-loads the core verb and result-passthrough behavior, then adds refusal routing, then the safety caveat, then a single example. Every sentence carries a distinct fact and the example earns its place by demonstrating the two-field call shape.

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 two-parameter passthrough dispatcher with no output schema, the one thing an agent needs is what comes back — the description answers that ('its own errors too', result returned unchanged). Combined with inherit-permissions disclosure and the call example, nothing essential is absent.

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%, so the baseline is 3; the description goes further with a worked example showing name paired with an arguments object, making the passthrough relationship concrete. It does not explain how per-tool parameter schemas are discovered or how to handle argument mismatches.

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 and resource ('run a tool found with integration_search and return its result unchanged') and implicitly contrasts with the sibling integration_search, which only discovers tools. An agent can tell execution apart from discovery 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?

Explicitly routes the agent: names must come from integration_search, and an uncallable name is refused with a pointer back to integration_search. It also gives an operational rule for destructive targets ('confirm such steps as you would there'), so when-to-use and when-to-be-careful are both stated.

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