tg_structure

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does a good job by detailing what data the tool returns (counts, unread, pinned, archived, folders) and how the 'sample' argument affects output. It does not explicitly state read-only safety, but the meaning of 'map' strongly implies a non-mutating overview.

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 compact: two sentences plus a single args line. It front-loads the core purpose in the first line, provides usage context in the second, and explains the parameter without any fluff.

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?

The tool is a single-parameter, account-wide overview with an output schema, and the description covers what data is returned and when to use it. It is complete enough for an agent to select and invoke the tool correctly; edge cases like pagination or folder depth are not mentioned, but the output schema should handle return structure.

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 only parameter 'sample' has 0% schema description coverage, so the description must compensate. It does so by explaining 'also include this many example chats from the main list and archive,' adding real meaning beyond the type/default already in the schema. It does not specify allowed ranges or behavior for negative values, but it is sufficient for standard use.

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 'Map of the whole account in one call' and then enumerates specific data categories: counts by type, unread, pinned, archive, and folders. It also says 'Start here when asked about the shape of the account rather than about one conversation,' which clearly separates it from per-conversation sibling tools.

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 gives an explicit when-to-use instruction: 'Start here when asked about the shape of the account.' It also provides a clear when-not ('rather than about one conversation'), though it does not name a specific alternative sibling tool such as tg_dialogs or tg_chat_info.

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