list_conversations

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: field shape in compact mode, cursor/hasMore/nextCursor pagination contract, and a hard cap of 20. It stops short of describing error conditions or ordering guarantees beyond 'newest first'.

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?

Four short sentences, front-loaded with the core action, then mode semantics, then the alternative-tool routing, then pagination constraints. No filler and nothing buried.

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 no output schema, the description carries the return-shape burden and does so partially: it names the compact fields (id/ts/summary/user/origin) and the pagination envelope (hasMore/nextCursor), but leaves the 'full' mode's raw row structure undefined. Sufficient to call correctly, slightly thin on what 'full' actually returns.

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 coverage is 100%, so the schema already documents each parameter; the description still adds value by restating the compact/full payload difference and the pagination rule that page should not be bumped without a cursor. The max limit=20 restatement duplicates the schema's 'max: 20' but reinforces the constraint.

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 ('List conversations for an agent'), adds ordering ('newest first'), and implicitly scopes the result set. It is clearly distinguishable from siblings like get_conversation, query_conversations, and get_conversations_bulk, which the description explicitly routes toward.

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 says to use get_conversation or get_conversations_bulk for message bodies, and warns 'do NOT bump page alone' in favor of cursor pagination. It also names the default mode, so the agent knows what it gets without specifying anything.

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