get_scoresRetrieve headline scores for every model RealRun tested on a task, ranked best first with cost tier and metric definition. Use the task id to compare AI model performance.
Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task id, e.g. 'receipts'. See list_tasks. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful behavioral context (results returned best-first, each row carrying cost tier and the metric definition), but says nothing about freshness, pagination, or how many models are returned.
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?
One sentence, front-loaded with the resource and its ordering rule; every clause adds information (scope, sort, payload) and none is redundant with the name or title.
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 does the work of describing the return shape (scores plus cost tier plus metric definition), which is what an agent needs. Only minor gaps remain, such as result-set size or staleness — low stakes for a read-only lookup.
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% with a single enum-constrained 'task' parameter already documented, including a cross-reference to list_tasks. The description adds no parameter detail, so the schema alone carries this dimension — the 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?
States a concrete verb+resource ('Headline scores for every model RealRun tested on a task') plus scope, ordering and payload. It is distinguishable from recommend_model (picks one) and list_tasks, though it never names those siblings explicitly.
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?
Usage is only implied — 'every model' hints this is the comparison/overview call versus recommend_model's single pick, but there is no explicit when-to-use or when-not-to-use statement and no alternative named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.