Skip to main content
Glama

Update problem

update_problem
DestructiveIdempotent

Replace an existing problem's specification and rebuild it; if the new spec fails, the original problem is preserved.

Instructions

Replace a problem's spec and rebuild it. The old problem is kept if the new spec fails to build.

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": {
      "problem_id": "<problem_id>",
      "spec": "<spec>"
    },
    "name": "update_problem"
  }
}

Input Schema

NameRequiredDescriptionDefault
specYes
problem_idYes

Output Schema

NameRequiredDescriptionDefault
nameNo
errorNo
inputsNo
statusNo
outputsNo
workdirNo
warningsNo
objectiveNo
problem_idNo
constraintsNo
design_varsNo
n_subsystemsNo
captured_outputNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

The description adds genuinely new behavior beyond the annotations: the atomic rollback guarantee that the old problem survives a failed build. That is real value on top of idempotentHint/destructiveHint. However, it does not say what is lost on success — prior recordings, case data, or a running driver — which matters for a tool flagged destructiveHint=true.

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?

Two sentences, zero waste, with the action front-loaded and the safety guarantee immediately after. Nothing could be removed without losing meaning.

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 and the spec schema is extremely detailed, so return values and structure need no prose. Still, for a destructive, idempotent mutation of a complex problem, the description leaves open what happens to recorded cases, existing results, and whether the problem must be idle — gaps an agent would want closed before calling it.

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

Parameters2/5

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

Top-level schema description coverage is 0%: neither problem_id nor spec carries a description, and the tool description never mentions either. The nested $defs are richly self-documenting, but nothing explains the contract between the two top-level parameters — e.g. whether problem_id must reference an existing problem or what happens if the name inside spec differs from problem_id.

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?

The description uses a specific verb ('Replace') on a specific resource ('a problem's spec') plus the consequence ('rebuild it'), which distinguishes it from create_problem or load_problem in spirit. It stops short of naming or contrasting any sibling explicitly, so it lands at a clear-but-undifferentiated 4.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no stated prerequisites (must the problem already exist? must it be closed or unrun first?), and no alternatives named such as create_problem or load_problem. The agent must infer that this applies to an existing problem_id from the word 'Replace' alone.

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