search_docs

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered and the description only needs to add context. It adds the cross-corpus reach and the `game`-includes-general-docs rule, but says nothing about ranking, ordering, or what happens when results exceed the limit cap of 50.

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?

Purpose is front-loaded in the first sentence with the routing table following, and there's no filler. The routing block is a dense run-on with inconsistent formatting (get_convar(name) vs get_entity('side:classname')), which slightly hurts scannability.

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?

An output schema exists, so return values need no explanation, and the routing table tells the agent what to do with each hit. Still missing is search-behavior context an agent needs to call correctly at scale: ranking order, and the fact that limit caps at 50 with no described pagination.

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 75% and already documents `query`, `game` and `kinds`; the description's "With `game` set, general docs are included too" adds non-obvious semantics beyond the schema. `limit` remains undocumented in both places (default 15, hard max 50, no paging described), which is the only substantive gap.

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?

"Full-text search across everything" names a specific verb and scope, and the kind→tool routing table immediately separates it from setup tools like list_convars, list_docs or search_pulse. An agent can tell exactly what this tool covers and where each result leads without opening another schema.

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 per-kind routing (convar→get_convar, pulse→search_pulse, doc→get_doc) effectively tells the agent which sibling to call for follow-up, and the `game` note explains a scoping behavior. It stops short of saying when to prefer this over sibling listers (e.g. list_docs vs a full-text search) or when not to use it.

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