Skip to main content
Glama

check_run

DestructiveIdempotent

Queue data and artifact validation checks—file contents, CSV/JSON bounds, thermo, trajectory, energy drift—to confirm required evidence without advisory or candidate results revoking it.

Instructions

Queue checks of existing data; no physics. Each has kind,path and optional unit,basis,role (required/advisory/candidate). Candidate/advisory results never revoke required evidence. file: min_bytes,contains; csv: columns,min_rows,bounds; json: values,bounds; thermo: phase={fix_id,style,group,marker,timestep}, columns,min_rows,energy_column,max_abs_drift,time_column. Use log_phases facts; block is a legacy selector. Raw energy drift during heat/work exchange needs a task-specific basis and balance=task_specific or an accounted energy column. trajectory: columns,min_frames,atoms; energy_jump: before_block,after_block,column,expected,tolerance. artifacts binds companion files. Read operation_get/check_get.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "checks": "<checks>",
      "op_id": "<op_id>"
    },
    "name": "check_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
op_idYes
tokenNo
checksYes
task_idYes
revisionYes
artifactsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description is consistent with that by framing the tool as queueing work. It adds real semantic context beyond the annotations, notably that candidate/advisory results never revoke required evidence and that certain energy-drift checks require a task-specific basis or accounted energy column. It never explains the destructive side (e.g., whether re-queueing supersedes prior results) or any permission/lifecycle constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Total length is defensible given the number of check kinds, and the scope statement is front-loaded. But the bulk is a semicolon-chained field dump with no grouping or formatting, making it slow to parse and easy to misread as prose requirements rather than as a schema reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. Still, for a tool with six parameters at 0% schema coverage, the definition omits any description of task_id, revision, and op_id semantics and gives no indication of preconditions for queueing checks against an existing task revision.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, and it does so well for `checks` (kind, path, unit, basis, role, plus per-kind fields for file/csv/json/thermo/trajectory/energy_jump) and partially for `artifacts`. It says nothing about task_id, revision, op_id, or token, leaving the four required parameters—including the idempotency key—entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Queue checks of existing data') plus a scope-exclusion ('no physics'), which lets an agent tell it apart from physics-execution siblings. The residual weakness is that what a 'check' actually is must be inferred from the subsequent field enumeration rather than from a plain-language sentence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers some routing hints ('Use log_phases facts; block is a legacy selector', 'Read operation_get/check_get'), which point to related tools and deprecate one argument path. However, there is no explicit when-to-use versus the clearly related siblings (checker_check, completion_check, validation_check), so selection guidance is only implied.

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