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

With no annotations provided, the description must carry the burden of behavioral disclosure. It mentions the pre-auth token is sensitive and that every response includes `_request_id` in structuredContent, adding useful context. However, it doesn't explain what happens to the session data, whether the token is consumed or persists, or any rate limits or side effects, leaving gaps for an operation that retrieves sensitive data.

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?

The description is three sentences, each earning its place: it states the core purpose, gives explicit auth-routing guidance, and notes a key response field. It is front-loaded with the primary action and does not waste words.

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?

Given the tool's moderate complexity (3 parameters, output schema present), the description covers the essential decision point (which token to use) and alerts to a sensitive field. It lacks detail on error conditions, whether the session requires ownership, or how the transcript is returned (though output schema covers return shape). Given the presence of an output schema and the focus on auth, it's adequately complete, missing only non-critical edge-case info.

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 coverage is 67%: both auth_token and onboarding_session_token have descriptions, but onboarding_session_id only has a pattern without a description. The description adds crucial value by clarifying when each auth parameter is used (JWT for user sessions, pre-auth token for pre-auth sessions), which the schema doesn't convey. This compensates for the missing description on the session ID parameter.

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 retrieves a replayable onboarding transcript and mentions two distinct authentication paths making it identifiable. It doesn't explicitly contrast with sibling tools sharing a 'get_' prefix, but the focus on onboarding sessions is distinct enough.

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?

The description provides clear guidance on when to use the JWT vs the pre-auth token, which is critical for the agent to choose the right authentication. It doesn't explicitly say when not to use this tool versus alternatives like get_status or list_sessions, but the authentication differentiation offers sufficient context.

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