list_messages

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds behavioral context by specifying the ordering as 'newest first' and the ability to filter by folder or unread status, which goes beyond the annotations. However, it does not disclose pagination behavior via top/skip or the default scope when no folder is specified.

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 a single sentence of 13 words, front-loaded with the verb and resource. It is concise and every phrase adds value: 'newest first', 'folder', 'unread only' are all meaningful details without redundancy.

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 has 4 optional parameters and an output schema, the description covers the essence of listing messages and the filters, but omits pagination semantics (top/skip). The output schema handles return values, so the primary gap is the lack of guidance on how to page through results or the default page size, leaving the agent partially under-informed.

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 explicitly mentions folder and unread filters ('Optionally restrict to a folder or unread only'), but it does not explain the top and skip parameters, which are crucial for pagination. The agent must infer their meaning from property names/defaults, making the description insufficient for full parameter understanding.

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 the verb 'List' and resource 'messages', with specific ordering ('newest first') and optional filters ('folder or unread only'). This distinguishes it from sibling tools like search_messages (search) and get_message (single message retrieval).

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?

The description implies usage for listing messages, optionally restricted by folder or unread status, but it does not explicitly contrast with alternative tools. Sibling tools such as search_messages or get_message could serve related purposes, yet no exclusions or guidance on when to choose this tool over them is provided.

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