List conversation transcripts

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

Since no annotations are provided, the description carries the full burden. It states 'Read-only' (safety), 'Needs a cached cs_login' (auth prerequisite), and 'newest first' (ordering behavior). It also discloses the scope of returned data. It doesn't cover rate limits or failure modes, but for a list tool this is adequate and exceeds what a minimal description would provide.

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 exactly two sentences. The first front-loads the purpose and output content; the second covers safety, auth, and the key sibling relationship. No filler, every clause earns its place, and it is easy to scan.

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 (9 optional params, no output schema, no annotations), the description covers the essential context: what it returns, the read-only behavior, the auth requirement, and the intended workflow (find session → get full transcript). It doesn't mention pagination or response volume, but that's arguably beyond what's needed for correct invocation, and the parameter schema already covers limits. Overall it is sufficiently complete.

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 schema already documents all nine parameters (top, days, botId, search, outcome, etc.) with their defaults and constraints. The description adds only general context about the content of the returned list, not parameter-specific guidance. It doesn't go beyond the schema's explanations, so it meets the baseline for full coverage without adding value.

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 states a precise action ('List conversation transcripts') and resource, then enumerates exactly what is returned ('when, how many turns, the first thing the user asked, which topics and tools fired, and how the session ended'). It also differentiates from the sibling tool by naming cs_get_transcript as the follow-up, leaving no ambiguity about scope.

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?

It provides a concrete use case ('find the session behind a bad answer') and explicitly routes the agent to cs_get_transcript for the full turn list, which acts as a when-to-use guide. It also notes the prerequisite 'Needs a cached cs_login'. It doesn't list explicit scenarios where this tool should NOT be used, but the context is clear enough.

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