tg_dialogs

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

With no annotations, the description carries the full burden and explains filter semantics, folder behavior, and output characteristics like recency, unread counts, and links. It doesn't mention pagination or a read-only guarantee, but for a list operation the behavior is well described.

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 concise and well-organized: a single-sentence summary followed by a clean parameter list. Every line serves a purpose, with no redundant or vague phrasing.

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 all parameter semantics and gives a key behavioral insight about the account's archiving habits. Output schema exists, so return format is likely specified there. Minor missing details like pagination and link format hold it back from a perfect score.

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?

The schema has 0% description coverage, but the description thoroughly documents all five parameters with concrete meanings and nuanced tips (e.g., archived null behavior, kind values). This fully compensates for the schema gaps and adds practical value.

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 opens with 'List chats (most recent first) with unread counts and links', which clearly states the action, resource, and key output features. This distinguishes it from sibling tools like tg_chat_info (single chat details) and tg_unread (unread messages only).

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 practical usage guidance, especially for the `archived` parameter ('pass null when searching for a chat rather than browsing the main list') and `kind` ('answers "what groups am I in"'). Doesn't explicitly name alternative tools or exclude use cases, but gives clear context for effective use.

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