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

Annotations already declare the tool read-only and idempotent, so the bar for additional behavioral disclosure is lower. The description adds meaningful context: `min_raters` overrides the ranking's configured value, and `api_key` behaves differently on the public endpoint vs `/mcp/mcp`. This goes beyond what annotations and schema provide.

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 compact and front-loaded: the first line states the purpose and output, followed by two short parameter clarifications. The unexplained phrase 'Layer 5' is mildly cryptic and prevents a perfect score, but it is not wasteful.

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?

For a read-only, idempotent metrics tool with an output schema and one required parameter, the description is largely complete. It covers the core return value, the auth nuance, and the override behavior. It is missing only explicit guidance on which scenarios make agreement calculation meaningful, but that is not critical for correct invocation.

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 carries the burden, and it does so for two of three parameters: `min_raters` is explained as an override, and `api_key` is clarified with endpoint-specific behavior. `ranking_id` is left implicit, but its role is recoverable from its name, required status, and the tool's stated purpose.

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 names the resource (inter-annotator agreement) and lists the exact metrics returned (Cohen's κ, Fleiss' κ, Krippendorff's α, Scott's π, plus a coverage report), making the tool's purpose unmistakable. The `ranking_id` parameter anchors it to a specific object, and the metric list distinguishes it from the many sibling `get_*` 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?

No guidance is given about when to pick this tool over siblings such as `get_crowd_bt`, `get_ceiling`, or `get_leaderboard`. The description only explains parameter overrides and endpoint auth behavior, so the agent must infer usage from the tool name and return behavior.

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