Skip to main content
Glama
kompas-mcp

kompas-mcp

by biryak

Specification rows

spec_edit
Destructive

Add, edit, or delete manual rows in KOMPAS specification (.spw) sections like Documentation, Materials, and Components; check before data to handle changes safely since KOMPAS has no row undo.

Instructions

Rows of a specification (.spw) that do not come from the model: Документация, Прочие изделия, Материалы, Комплекты (ГОСТ 2.106). inspect_model on the .spw lists them with ids (free_rows). Positions are filled by KOMPAS by its own settings. NOTE: KOMPAS keeps no Undo for specification rows — the result has before; delete rows only with the user's consent.

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": {
      "doc": "<doc>"
    },
    "name": "spec_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
addNonew rows {section: 'Документация'|'Прочие изделия'|'Материалы'|'Комплекты', name, designation?, quantity?, note?, format?} — e.g. the assembly drawing «Сборочный чертеж» with its designation, a bought motor, a sealant with quantity and unit in note
docYesDocument handle from doc_list/doc_open, e.g. 'doc:12001:0a1b2c3d'
editNo{id, field: new text…} for free rows
deleteNoids of free rows to delete

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, but the description goes well beyond them by disclosing that KOMPAS keeps no Undo for specification rows, that the result carries a `before` payload for recovery, and that deletions must be done only with user consent. These are exactly the operational and safety facts an agent needs before issuing a destructive edit.

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?

The scope statement is front-loaded, then the id-discovery hint, then the safety NOTE — a sensible ordering with little filler. The opening noun phrase is slightly terse and the abrupt jump into the NOTE leaves the read/write action implicit, but nothing is wasted.

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 destructive, non-idempotent mutation tool with no output schema, the description covers the essentials: which rows are in scope, how to get ids, the absence of Undo, and the `before` recovery payload. It does not describe the response shape or what a partial failure across add/edit/delete would look like, but the safety-critical information is present.

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 coverage is 100% and the add/edit/delete properties already carry detailed descriptions with examples, so the schema does the heavy lifting. The description adds only marginal meaning beyond that — chiefly that positions are assigned by KOMPAS, which explains why callers don't supply a position field. Baseline 3 applies.

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 names the specific resource and its scope boundary: rows of a .spw specification that do NOT come from the model, enumerating the four free-row sections (Документация, Прочие изделия, Материалы, Комплекты). The edit verb itself is only implicit (surfaced by the add/edit/delete schema), and no sibling such as spec_create is named for contrast, so it falls just short of a 5.

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?

It gives a concrete prerequisite path — inspect_model on the .spw lists free rows with their ids — which tells the agent where the ids it needs come from. It also sets a clear domain boundary ('Positions are filled by KOMPAS by its own settings', i.e. this tool covers free rows, not model-derived ones), though it does not explicitly say when to use spec_create instead.

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