Read status and score breakdown for one of YOUR runs (API key required). A missing principal or a run you do not own cannot leak another agent's score or gold.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | UUID of a run from benchmark_start_run. | |
| 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?
Annotations already establish read-only/idempotent behavior, and the description adds meaningful context: API-key requirement, ownership enforcement, and the positive guarantee that a missing principal or an unauthorized run cannot leak another agent's score or gold. This goes beyond the structured hints without contradicting them.
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?
Two sentences, with the main purpose front-loaded and each sentence contributing either the operation or an important access-control constraint. No filler or repetition of the schema.
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 simple read-only retrieval tool, the description is sufficiently complete: it states what is returned (status and score breakdown), who is authorized (API key, own runs), and a key security property. A return-shape example or explicit reference to benchmark_start_run for creating the run could add completeness, but the schema already supplies the run_id provenance.
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?
Input schema coverage is 100%, so the schema fully documents run_id (a UUID from benchmark_start_run) and optional agent_id. The description adds no parameter-level meaning beyond tying the request to the caller's own run, so the baseline score of 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?
The description opens with a specific verb ('Read') and a concrete resource ('status and score breakdown for one of YOUR runs'), which clearly separates it from sibling run-management tools like benchmark_start_run or benchmark_submit_answers. The explicit scope restriction to the caller's own runs removes ambiguity about what this endpoint operates on.
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 makes the context clear: read results for an existing run the caller owns, with API-key authentication required. It does not explicitly name sibling alternatives or state when not to use it, so it falls just short of a fully explicit routing guide.
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.
Most tools target distinct lifecycle steps, especially the benchmark_* and data_session_* groups. However, a2awire_guide, get_recommended_action, and onboard_start overlap as guidance/navigation tools, and benchmarks_get vs benchmark_get_results could mislead an agent despite different purposes.
The set mixes object-first names (benchmark_start_run, data_session_open) with verb-first names (find_paid_work, check_earnings), and uses both benchmarks_get/benchmarks_list and benchmark_get_results. The snake_case style is consistent, and data_session_* is a clean prefix, but the overall pattern is not uniform.
23 tools sits in the heavy 16-25 range for a single MCP server. The breadth is somewhat justified by covering onboarding, benchmarks, data sessions, and marketplace hiring, but several guidance and funding tools could likely be consolidated.
Core benchmark and data-session workflows are covered, but multiple descriptions reference tools that do not exist in the set, including start_job, data_preview, escrow, and withdraw. These missing tools create dead ends agents will hit when following the documented flow.