Skip to main content
Glama
Sign In
ecu-harness

ecu-harness

by omaratif1995
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Edit the configuration

ecu_edit

Apply all-or-nothing, type-checked edits to AUTOSAR ECU configuration with consistent references and validation; preview changes with dry runs and review findings before writing.

Instructions

Change the configuration. All ops succeed together or nothing is written; values are type-checked, references stay consistent, and the result lists new findings. The first call needs 'goal' and opens a change.

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": {
      "ops": "<ops>"
    },
    "name": "ecu_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
opsYesOperations, applied in order.
goalNoOne sentence: what will change and why. Needed when no change is open.
ticketNoOptional ticket or requirement id, stored with the change.
dry_runNoCheck the ops and show the result without writing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare write, non-idempotent, non-destructive, closed-world behavior. The description adds genuine value beyond that: atomic all-or-nothing application, type checking, reference consistency, and a returned finding list. It stops short of disclosing what the result actually contains (change id? findings format?) or how a staged change is later committed, so a 3 is fair rather than a 4.

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

Conciseness4/5

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

Three compact sentences, with the transactional guarantee and the goal-on-first-call rule front-loaded where an agent will read them. The opening 'Change the configuration' largely restates the title, which is the only wasted clause.

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?

For a mutation tool with no output schema, the description should characterize the return value and the change lifecycle; it only says 'the result lists new findings,' which is thin. It also leaves the relationship to ecu_change_finish / ecu_change_discard entirely implicit, so an agent may not know how to conclude the opened change.

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?

Schema description coverage is 100%, so the schema already documents every parameter, including 'goal' being needed when no change is open and ops being applied in order. The description merely restates those schema facts and adds no new meaning about op semantics, ordering edge cases, or dry_run behavior, so it sits below the baseline-3 case where the schema does the heavy lifting unassisted.

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 concrete verb (change) plus the resource (the configuration) and explains the mechanism precisely: an ordered list of ops applied atomically. It implies a staged-change workflow ('opens a change'), which distinguishes it from siblings like ecu_change_finish/discard, but never names those tools or states what 'configuration' covers.

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?

Provides one useful workflow cue: the first call needs 'goal' and opens a change, implying subsequent calls target the open change. It gives no explicit guidance on when to prefer this over alternatives (e.g. ecu_validate, ecu_change_diff, ecu_change_finish) or how to abandon a change.

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

Deploy Server

Other Tools