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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds useful behavioral context beyond those hints: 'api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.' This endpoint-specific auth nuance is not carried in annotations or schema and is relevant for successful invocation.

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 description is three short sentences, each serving a distinct purpose: defining the metric, stating the decision-use context, and flagging endpoint-specific auth behavior. There is no filler or redundant restatement of the tool name.

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 an output schema present and safety annotations already covering read-only/idempotent behavior, the description is mostly complete. The main gap is parameter-level semantics, particularly min_overlapping_items and the exact meaning of ranking_id. The domain-specific ceiling context and auth nuance make it close to fully self-sufficient.

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 0%, so the description must compensate for parameter documentation. It adds meaning for api_key (optional/refused context) and implies ranking_id connects to the ranking domain, but it does not explain min_overlapping_items or specify what ranking_id must reference. Coverage is too incomplete for a low-coverage schema.

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?

The description states the tool's purpose with a specific verb and resource: 'Pairwise-κ ceiling from qualification attempts.' It also defines the output concept as 'the upper bound any judge / RM can credibly hit on this domain,' which distinguishes it from sibling metrics like agreement or Plackett-Luce. The description is neither tautological nor vague.

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 description gives concrete usage context: the result is 'used to pin the L3 pilot refund clause (refund if κ < ceiling - 5pp).' This tells an agent when the value matters. It does not explicitly name alternatives or exclusions, but the context is sufficiently clear for selection among sibling tools.

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