list_messages

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

With no annotations, the description carries the full burden and does well: it discloses ordering, pagination behavior (page, page_size ≤ 100), the non-destructive trait ('rien n'est marqué comme lu'), and a quota/transport nuance (headless browser, not API quota). It omits what a returned conversation looks like and any permission requirements, leaving some behavioral detail unstated.

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 purpose is front-loaded, followed by folder semantics, pagination, then behavioral caveats, in a tight multi-line format with little waste. Dense but each clause adds information; minor density could still be trimmed.

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?

For a four-parameter list tool with no annotations and no output schema, the description covers scope, ordering, folder semantics, pagination limits, and non-destructive behavior. The notable hole is the undocumented unread_only parameter and the absence of any hint about the return shape.

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 0%, so the description must compensate. It documents folder values (inbox/sent/all) and page/page_size with the ≤100 cap, covering three of four parameters, but says nothing about unread_only, which is left completely undocumented in both schema and description.

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 ('Liste les conversations de la messagerie Click n' Glide'), the ordering ('les plus récentes d'abord'), and explicitly distinguishes itself from the read tool by noting it does not open conversations. An agent can differentiate it from read_message, send_message, and list_recipients at a glance.

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?

Gives clear context for folder selection with inline definitions ('inbox' reçus, 'sent' où j'ai écrit, 'all') and clarifies the tool is read-only in effect (nothing marked as read). It does not, however, name an explicit alternative or state when-not-to-use this versus read_message, so it stops short of the full when/alternatives specification.

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