list_conversations

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

Without annotations, the description carries the behavioral burden. It makes clear this is a read-only, aggregated overview rather than a detailed or mutating operation. It could add more nuance about sorting or limit behavior, but the non-destructive, summary nature is evident.

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?

One focused sentence that front-loads the core behavior, then gives the output shape and a concrete use case. No wasted 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?

With an output schema present and a simple single-parameter input, the description covers the essential trigger and result semantics. The main missing piece is the limit parameter's behavior and how this relates to the sibling get_inbox tool.

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 only parameter, limit, has no description coverage, and the tool description never mentions it. Saying 'all this agent's conversations' could even mislead an agent into ignoring the default 50-row limit. The schema's title and default provide minimal meaning, but the description fails to clarify the parameter's effect.

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 what the tool does: it summarizes all of this agent's conversations, with one row per partner including last message and unread count. It is distinct enough as a resource-level operation, though it does not explicitly differentiate itself from the sibling get_inbox.

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 gives an explicit trigger context: 'Use as an inbox-style overview when the user asks who have I been talking to?'. This is strong usage guidance, but it stops short of naming alternatives or explaining when not to use it.

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