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

Goes well beyond the annotations: it discloses that credentials never pass through the tool, that the caller receives a { url, instructions } handoff for the user to complete in Stepper, and what follow-up calls confirm the result. This is exactly the kind of behavioral context annotations (readOnlyHint/idempotentHint) cannot express. The description is consistent with readOnlyHint=true — the tool itself only returns a URL rather than mutating state.

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 tight sentences with no filler, and the critical non-obvious fact (credentials never pass through) is front-loaded. The opening framing sentence is slightly indirect for a tool description but earns its place by setting up the flow.

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 an output schema present and rich annotations, the description only needs to explain the interaction flow — which it does thoroughly (handoff, credential handling, follow-up). Minor residue: it doesn't say what state the connection is in before the user finishes in Stepper, or how the caller learns the connection was completed beyond polling list.

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?

Only one parameter, and schema description coverage is 100% — the schema already states "the app id, exactly as list({ type: 'app' }) returned it." The description adds no further meaning about the parameter's format or source. Baseline 3 is appropriate when the schema does all the work.

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 conveys a specific verb+resource (connect an account for a workflow app) and, crucially, states that the tool does NOT perform the connection itself but returns { url, instructions }. The opening sentence is phrased as a topic ("How the user connects...") rather than a direct statement of what the tool does, which slightly blunts immediacy, but the operation is unambiguous and distinguishable from share_connection.

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?

Clear routing context: use this to start a connection, then share_connection if the connection should be shared with the space, then list({ type: "connection" }) to confirm. Explicit alternatives are named with the condition that selects them. No explicit when-not-to-use or prerequisite statement (e.g., that list({ type: "app" }) must be called first is left to the schema).

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