Skip to main content
Glama
io.github.chowdhurylab-studio/ipro-agent

io.github.chowdhurylab-studio/ipro-agent

ipro_cancel

Stops a running design after its current iteration and preserves written output so the best design found remains readable with ipro_result.

Instructions

Stop a running design. It stops after the iteration it is in and keeps what it has written, so the best design found so far is still readable with ipro_result. Only runs this server started, on this machine.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ipro_cancel"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNoor the id ipro_run returned
run_dirNothe run directory

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that termination is graceful (after the current iteration), that written state is preserved, and that results remain readable via ipro_result. It leaves out what the call returns, whether it is idempotent, and how the agent confirms the run actually stopped, which keeps it short of a 5.

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

Conciseness5/5

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

Three short sentences, front-loaded with the action, then the side-effect semantics, then the scope restriction. No sentence is redundant, and the ordering puts the most decision-relevant information first.

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

Completeness4/5

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

For a two-parameter mutation tool with no annotations and no output schema, the description covers the essentials an agent needs: what is stopped, what survives, and where to read results afterwards. It could say more about the response or verification, but nothing critical for correct invocation is missing.

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 100%, so run_id and run_dir are already documented in the schema; the description adds no meaning about which identifier to prefer or whether both are needed. Baseline 3 applies since the schema does the heavy lifting.

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 object ('Stop a running design'), so the agent knows this terminates an in-progress run rather than reading or scoring it. It implicitly distinguishes itself from ipro_result by naming that tool as the way to read results afterwards, though it never uses the run/cancel vocabulary that would tie it explicitly to ipro_run.

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

Usage Guidelines4/5

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

Gives a clear condition for use (a design is running and should be stopped) and names the alternative for the adjacent task (read results with ipro_result). It also states a real scope restriction — only runs this server started on this machine — which functions as a when-not rule, but there is no explicit guidance on what to do instead for external runs or already-finished runs.

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