list_messages

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

With no annotations, the description carries the behavior burden. It usefully discloses that this is a read operation, that results are ordered oldest first, and that after/before accept specific formats. It does not describe pagination behavior, from_me filtering semantics, or response contents.

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 tightly written sentences: the core function is front-loaded and the format note adds essential detail without bloat. Every sentence earns its place.

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?

Covers ordering and date syntax, which are the most important non-obvious traits. Gaps remain around pagination, filter behavior, and return shape, and since there is no output schema these omissions are more noticeable.

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%, but the description meaningfully documents the two ambiguous parameters, after and before, with concrete accepted formats. Limit, offset, and from_me are left to their titles and defaults, which are mostly self-explanatory.

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 the verb 'Read', the resource 'messages in one chat', and the ordering 'oldest first'. The phrase 'in one chat' distinguishes it from siblings like list_chats and search_messages, though it does not name them 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?

Implies usage when you need messages from a specific chat, and provides date-format guidance, but gives no explicit when-to-use vs. alternatives such as search_messages or get_chat_context. There is no exclusion guidance.

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