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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds real context beyond them: the operation is 'Instant' and the return is verbatim multi-model answers with the axes of divergence. It stops short of describing index size, pagination, or what a browse result entry looks like, which an agent choosing to browse would want.

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 tight sentences, front-loaded with what the resource is, then the mode switch, then the routing advice. Every clause carries information — no restatement of the tool name and no filler.

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 carries the burden of describing returns, and it does — verbatim model answers plus divergence axes. The remaining gap is the browse-index shape (whether it returns ids, titles, or snippets), which is hinted at only by 'a divergence record id (e.g. from the browse index)'.

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 100%, so the baseline is 3, but the description adds the combination semantics the schema leaves implicit: which mode each parameter triggers and that omitting id is the browse path. The id/search interaction is also covered ('search' is only a browse-index filter), giving the agent mode-selection meaning rather than just field definitions.

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 and resource — 'Read curated cross-model DIVERGENCE records' — and defines what a record contains ('verbatim answers from multiple frontier models ... plus the axes on which they split'). It also distinguishes itself from a named sibling ('prefer this over omnarai_council'), so an agent can choose without opening either 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?

Gives explicit branch logic: 'Omit id to browse the index (optionally filter with search); pass id to read one full record.' It names the alternative tool and the condition that selects it ('when an existing record may already cover the question'). Both when-to-use and when-to-prefer-else are covered.

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