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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description adds genuine behavioral context by disclosing return shape (capabilities grouped with their listings) and ordering semantics ('best first'), which no output schema provides. It stops short of describing pagination or how many results come back.

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 short clauses with no filler; what is returned comes first and the parameter note follows. Slightly telegraphic ('best first') but every phrase carries information.

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 what comes back, and it does (capabilities plus their listings, ranked). A single optional filter keeps complexity low, so this is nearly enough; only result volume / pagination behavior is unaddressed.

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 100% and the prefix parameter is already documented with examples in the schema. The description's 'prefix narrows it, e.g. web.' largely restates that, adding only the 'starts-with' narrowing intent rather than new format or edge-case detail.

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+resource: lists every capability the directory tracks with the listings providing it. The parenthetical examples (inference.llm, web.search, …) make the resource concrete and distinguish it from sibling tools like search_tools or get_tool, though it never explicitly contrasts with search_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?

Usage is only implied: 'prefix narrows it, e.g. web.' suggests a browse-then-narrow flow but does not say when to call this versus search_tools, or that it should be used for discovery rather than lookup.

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