compute_check
The door's and the machine's rules over a job (argv and every file) without running it; no model...
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | ||
| public | No | ||
| command | Yes | ||
| timeout_s | No | ||
| result_path | No |
The door's and the machine's rules over a job (argv and every file) without running it; no model...
| Name | Required | Description | Default |
|---|---|---|---|
| files | No | ||
| public | No | ||
| command | Yes | ||
| timeout_s | No | ||
| result_path | No |
Changes observed during successful MCP inspections.
Input schema / properties / command / descriptionRemoved value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionRemoved value: -"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionRemoved value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionRemoved value: -"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionRemoved value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionAdded value: +"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionAdded value: +"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionAdded value: +"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionAdded value: +"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionAdded value: +"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionRemoved value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionRemoved value: -"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionRemoved value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionRemoved value: -"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionRemoved value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionAdded value: +"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionAdded value: +"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionAdded value: +"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionAdded value: +"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionAdded value: +"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionRemoved value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionRemoved value: -"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionRemoved value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionRemoved value: -"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionRemoved value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionAdded value: +"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionAdded value: +"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionAdded value: +"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionAdded value: +"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionAdded value: +"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionRemoved value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionRemoved value: -"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionRemoved value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionRemoved value: -"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionRemoved value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / descriptionAdded value: +"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / files / descriptionAdded value: +"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / public / descriptionAdded value: +"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / result_path / descriptionAdded value: +"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / timeout_s / descriptionAdded value: +"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / command / items / propertiesRemoved value: -nullInput schema / properties / command / propertiesRemoved value: -nullInput schema / properties / files / propertiesRemoved value: -nullInput schema / properties / public / propertiesRemoved value: -nullInput schema / properties / result_path / propertiesRemoved value: -nullInput schema / properties / timeout_s / propertiesRemoved value: -nullInput schema / properties / command / descriptionRemoved value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"Input schema / properties / command / items / propertiesAdded value: +nullInput schema / properties / command / propertiesAdded value: +nullInput schema / properties / files / descriptionRemoved value: -"relative path -> text content, put in the job folder (source only, no binaries)"Input schema / properties / files / propertiesAdded value: +nullInput schema / properties / public / descriptionRemoved value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"Input schema / properties / public / propertiesAdded value: +nullInput schema / properties / result_path / descriptionRemoved value: -"file the job writes its answer to, default result.json; it comes back as output"Input schema / properties / result_path / propertiesAdded value: +nullInput schema / properties / timeout_s / descriptionRemoved value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"Input schema / properties / timeout_s / propertiesAdded value: +nullDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description reinforces that nothing is executed, but adds little about what rules are checked, what a failure looks like, or what is 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?
It is short, but the single sentence is cryptic and appears truncated ("no model..."), so it is not front-loaded with a clear purpose. Brevity here reflects under-specification rather than efficient structure.
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 five parameters, zero schema description coverage, a nested files object, and no output schema, the description is far too thin. It does not explain the validation outcome or how the check relates to compute_submit.
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 0%, so the description must compensate, but it only vaguely gestures at argv and files. It says nothing about public, timeout_s, or result_path, leaving most parameters unexplained.
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 says it checks a job "without running it," which hints at validation, but the phrasing "The door's and the machine's rules over a job" is opaque and never states a clear verb+resource. It does not distinguish compute_check from siblings such as compute_submit or compute_quote.
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?
There is no explicit guidance on when to use this versus compute_submit, compute_quote, or other compute siblings. "Without running it" weakly implies a preflight check, but no alternatives or exclusions are named.
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.