Trigger isolated benchmark evaluations with a benchmark ID, scoring 0-100. Use query mode to inspect logs without running new tests.
Benchmark 评测——传 benchmark_id 触发隔离评测（评分 0..100）；query 查日志。
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | 查询模式（true = 只查日志不触发新评测） | |
| case_id | No | Case ID（缺省 = 评测全部 cases） | |
| benchmark_id | Yes | Benchmark ID（必填） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that evaluation is 'isolated' and that scores range 0..100, which is useful. It also distinguishes a read-only query mode. However, it does not mention side effects, prerequisites, cost, or what happens to existing data when evaluation triggers. It is not misleading but leaves important behavioral gaps.
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 extremely concise, just two short clauses that introduce the tool and its two modes. It is front-loaded with the primary function. While it could be slightly more informative, it is not verbose or redundant, and every word earns its place.
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 tool that triggers an evaluation and queries logs, the description is thin. It lacks context on what 'evaluation' entails, what the output structure looks like (no output schema), what logs contain, and any side effects of triggering. It also does not explain when to use query mode versus evaluation mode in practical terms. Given the complexity and absence of output schema, this is insufficient.
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 schema already documents benchmark_id, query, and case_id. The description mentions benchmark_id and query in the context of modes, but adds no additional meaning beyond the schema. case_id is not referenced in the description, and the schema already explains its default behavior. Baseline 3 is appropriate since the schema handles semantics.
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 tool performs benchmark evaluation (Benchmark 评测) and mentions two modes: triggering an isolated evaluation with benchmark_id and querying logs. This is a specific verb and resource, not a tautology. However, it doesn't differentiate from siblings like evaluate_output or eval_suite, which also deal with evaluation, so it misses a point.
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 two usage modes (trigger evaluation vs. query logs) and notes that benchmark_id triggers evaluation, providing clear context. However, it does not explicitly mention when to prefer this tool over alternatives or any exclusions (e.g., when not to use it). It leaves differentiation to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.