list_messages

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the description's added value is real: it discloses result ordering, the direction of pagination, and that reactions, quoted replies, edits and deletions are merged into each message. That last point is meaningful behavioral context an agent would not infer from the schema.

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?

Two tight sentences with no filler, and the ordering constraint plus pagination hint are front-loaded. Nothing redundant is present; it could arguably state one routing rule for a perfect score.

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, return values need not be re-explained, and the description covers the two things an agent must know before calling: ordering semantics and how to page backwards. Nothing essential for correct invocation is missing.

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 88% with per-field descriptions, so the schema already explains chat, kind, limit, since/until, before and sender. The description only adds a conceptual link between the 'before' parameter and the 'next_before' cursor, which is helpful but marginal against the schema's own documentation.

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 ('Messages d'une discussion') plus the ordering contract (chronological, newest page first). It is distinguishable from siblings like search_messages or get_message_context, though it never names an alternative explicitly.

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?

Provides genuine usage direction for pagination ('next_before donne la page plus ancienne'), which tells the agent how to walk backwards through history. However, it gives no guidance on when this tool should be chosen over search_messages, list_recent, or get_message_context.

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