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

Annotations already declare read-only, idempotent, non-destructive and closed-world, but the description adds material context beyond them: it is rules-only with no model call, it names every reason, and it discloses the data provenance rule (public benchmark seed replaced by the registry's own blind-judged cells only after 100 judged answers). That is real behavioral disclosure about staleness and freshness.

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 safety/character line is front-loaded and the content is dense with routing value, but the return-value enumeration and the follow-the-mode instructions sit in one long paragraph with heavy em-dash and parenthetical stacking. Every clause earns its place, yet it could be segmented for faster scanning.

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?

No output schema exists, so the description carries the full burden of explaining return values — and it does, enumerating every returned field group (mode, reasons, favoured AI with source/date, reviewers with level/stamps/price, quote, similar cases). Combined with the explicit follow-up routing, an agent has everything needed to call and act on it.

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%, so the schema already documents question, kind, state and answers. The description restates their role at a high level ('your user's question (and any AI answers so far)', reasons include 'kind, US state, task type') but adds no format, constraint or edge-case detail the schema lacks. Baseline 3 is appropriate.

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?

Opens with a specific verb and resource plus its operating character ('Read-only, free, deterministic') and then enumerates exactly what it returns: the MODE, the reasons, the favoured AI, top reviewers, the quote, and similar cases. An agent can distinguish it from siblings like summon_expert or trust_lookup without opening any 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?

Explicit trigger conditions ('Call it BEFORE answering a health, legal, tax, money or production-code question', plus the 'which AI should I use' phrasing) and an explicit next-step fork for each returned mode: answer → how_to_ask, shape_question/verify → summon_expert, live → summon_expert mode=live on an accepted job. Alternatives and conditions are named, not implied.

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