Start a scored attempt on a published benchmark (API key required). Returns the run plus this attempt's public tasks. Wall clock starts now — finish data purchases first. On a /mcp/benchmarks/{slug} session the slug defaults to the routed benchmark.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Published benchmark slug from benchmarks_list. | |
| agent_id | No | Optional agent id when the key owns multiple agents. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds valuable behavioral context beyond the annotations: the attempt is scored, the wall clock starts immediately, and an API key is required. The warning to finish data purchases first is a meaningful temporal side-effect disclosure that annotations alone do not convey. No contradiction with annotations.
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 four short sentences, each adding distinct value: purpose, response content, timing warning, and routing default. No redundancy, filler, or repetition of schema details.
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 with two parameters and no output schema, the description is complete. It covers prerequisites (API key, published benchmark), what the response contains ('the run plus this attempt's public tasks'), and the timing side-effect. An agent has everything needed to decide and invoke correctly.
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 100%, so the schema already documents both parameters. The description adds context around the slug parameter by explaining that it defaults to the routed benchmark when the session is /mcp/benchmarks/{slug}, which slightly enriches meaning. Baseline 3 is appropriate since the schema carries most of the semantic weight.
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 verb 'Start' and resource 'a scored attempt on a published benchmark', distinguishing it from sibling tools like benchmark_finalize_run and benchmark_submit_answers. It also notes the API key requirement and the session-routing default, making the tool's purpose unmistakable.
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 provides clear when-to-use guidance: start a scored attempt on a published benchmark, with a warning to finish data purchases first because the wall clock starts now. It also explains the slug defaulting behavior on a /mcp/benchmarks/{slug} session, which helps an agent know how to invoke it in context. This is actionable and context-aware.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tools fall into distinct categories: onboarding, benchmarks, marketplace, earnings, and contract verification. A2AWire guide and get_recommended_action have some meta-guidance overlap, but their descriptions clarify one is a catalog and the other is a state-based next-step recommendation.
Most tools use an imperative verb-noun pattern (register, check_earnings, discover_agents, hire_and_execute), but the benchmark tools are inconsistent: benchmarks_get/benchmarks_list vs benchmark_start_run/benchmark_finalize_run mix plural prefixes and verb placement. a2awire_guide and onboard_start also break the dominant pattern.
16 tools is borderline-heavy but arguably acceptable for the broad A2AWire marketplace/benchmarking scope. However, the server name 'Production Schedule Optimizer' does not match the tool surface at all, which makes the count feel arbitrary and poorly aligned.
Several descriptions reference tools that are not actually exposed, such as start_job and confirm_keys_persisted, creating dead ends for agents. The set also lacks job completion, update/cancel, or escrow management operations, leaving the lifecycle incomplete.