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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description need not repeat those. It adds valuable behavioral context: ordering ('newest first'), output fields (per-round points, totals, deductions, flags for dissents/split panels, colleague totals), and scope ('Commission records only'). This goes beyond annotations and informs the caller about what to expect. No contradiction found.

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 concise sentences, front-loaded with the core purpose. It wastes no words and packs relevant detail about output contents. It is slightly dense but remains readable. A minor improvement could be to separate the output fields from the scope note, but overall it is well-structured and efficient.

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 list endpoint with no output schema, the description provides a fairly complete picture of the response (per-round points, totals, decision type, deductions, flags, colleague totals). It also covers ordering and scope. However, it does not explicitly mention pagination or how limit/cursor affect results, which could be considered standard but are not clarified. Given the annotations and the tool's simplicity, this is adequately complete, though a brief note on pagination would push it to 5.

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 only 33%: the description explains judge_id ('from list_judges') but omits any explanation for the limit and cursor parameters. These are not self-evident to a generic agent (cursor especially), and the description does not compensate for the low coverage. The description adds value only for the required parameter, leaving two optional parameters undefined. Given the low coverage, a more thorough explanation was needed.

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 clearly states the specific resource (a judge's official scorecards) and the exact content (per-round points, totals, decision type, deductions). It also adds critical scope ('Commission records only') and distinguishes from siblings like get_judge (judge metadata) and list_judges (list of judges) by describing unique fields and flags. The verb 'get' plus resource makes the purpose unambiguous.

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 implies when to use (when you need a specific judge's scorecards) but does not explicitly compare with alternatives or state when not to use. It mentions 'From list_judges' for the judge_id parameter, hinting at a workflow, but lacks explicit guidance like 'For judge profiles use get_judge instead.' The usage context is partially implied but not fully spelled out.

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