Categories

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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, and the description still adds genuine behavior: the hierarchical structure of the result, the rule that sub-categories require a group id, and the domain quirk that audio slugs end in «-صوتی». It stops short of describing result size, pagination, or whether groups and standalone categories are mixed in one flat list.

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?

Three compact sentences with the structural definition front-loaded and the parameter rules following, no filler. Minor cost: "Pass an id or slug to the list tools" is vague about which tools, forcing a glance at the sibling list.

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 two-parameter, no-output-schema read tool this is close to sufficient: the return shape (groups with ids, categories with slugs) is sketched and the group semantics are explained. It is not complete — the format filter is undocumented and the exact shape of the returned tree (nesting depth, whether slugs are per-locale) is left ambiguous.

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 coverage is only 50%, and the covered parameter's schema text ("Group id: only it, with sub-categories") is cryptic — the description usefully clarifies that group=<id> scopes the response to that group's sub-categories. However, the format parameter (any/ebook/audiobook) is never mentioned in either schema text or description, leaving the agent to guess what filtering it performs and how it interacts with the «-صوتی» slug convention.

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 names the resource precisely ("Category tree: top-level groups (id) and standalone categories, each with a slug") and implicitly states the verb — enumerate/fetch the taxonomy. It also hints at its role as a feeder tool ("Pass an id or slug to the list tools"), which separates it from the browsing/search siblings, though it never explicitly names an alternative.

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?

There is real usage guidance in the workflow sense: use the returned id/slug in the list tools, and use group=<id> to reach sub-categories. What is missing is any statement of when to call this tool versus tg_browse or tg_search, or any prerequisite/exclusion — the agent must infer that this is the entry point for taxonomy discovery.

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