list_categories

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

No annotations are provided, so the description must carry the behavioral load. It declares 'Read-only' and discloses that counts are included, which is valuable. However, it says nothing about response size, ordering, caching, or whether the taxonomy list is complete — modest gaps for an unannotated tool.

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 compact sentences, front-loaded with what is listed, followed by the follow-up action. Nothing restates the name or wastes tokens.

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?

With no output schema, the description must convey return content, and it does: categories with counts plus field tags with examples. It stops short of describing the response shape (flat list vs object with two keys), which is the only real gap for such a simple tool.

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?

There are zero parameters, which is the baseline-4 case. The description reinforces that no filtering input is needed by framing the call as a full taxonomy listing.

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 a specific verb ('List') and resource ('the catalogue's taxonomies'), then enumerates exactly what comes back: AI-tool categories with counts and field tags with example values. This distinguishes it clearly from get_tool (single fetch) and search_tools (query-driven search).

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?

'Useful for then calling search_tools with a category' gives an explicit downstream use and names the sibling it feeds. It lacks an explicit 'do not use this if...' exclusion, but the usage context is unambiguous for a zero-param discovery tool.

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