Skip to main content
Glama
Disectron

twincat-mcp

by Disectron
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

hw_search

Read-only

Full-text search of the ESI index: devices (names, PDOs and their entries, PDO assignments), CoE objects (names, descriptions, sub-index names), diagnosis messages (text, description, causes, remedies) and modules.

Instructions

Full-text search of the ESI index: devices (names, PDOs and their entries, PDO assignments), CoE objects (names, descriptions, sub-index names), diagnosis messages (text, description, causes, remedies) and modules. kinds: any of 'device', 'object', 'diag', 'module' (default all; a module is found by its own name and PDOs and by the devices whose slots take it — type, name, group). FTS5 syntax (words ANDed, "phrase", prefix*); other text is searched as one phrase. Hits with the same title (revisions of one type, one text in several catalogues) are one item with variants; objects and messages name the device types that have them. Pages: total items, offset / next_offset; a limit above 100 is used as 100 (clamped).

Input Schema

NameRequiredDescriptionDefault
kindsNo
limitNoitems per page, 1-100; a larger limit is used as 100 (clamped: true)
queryYes
offsetNoskipped first: the next page is offset=<next_offset>

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.18
    • addedInput schema / properties / limit / description
      Added value: +"items per page, 1-100; a larger limit is used as 100 (clamped: true)"
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "skipped first: the next page is offset=<next_offset>",
+  "minimum": 0,
+  "title": "Offset",
+  "type": "integer"
+}
  2. Addedv0.8.12

TDQS

A4/5.0
Behavior5/5

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

Goes well beyond the readOnly/destructive annotations by disclosing query parsing (FTS5: terms ANDed, quoted phrases, prefix*, otherwise a single phrase), result aggregation (hits sharing a title collapse into one item with `variants`; objects and messages list the device types that have them), and pagination clamping (limit above 100 used as 100). These are non-obvious behaviors an agent would otherwise only discover by trial.

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?

Front-loaded with what is searched, then kinds, query syntax, result grouping, and paging in that order; every clause carries information. It is a dense wall of text with parentheticals that take care to parse, but little 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 multi-entity search with a 4-parameter schema and an output schema, the description covers query semantics, kind coverage, result collapsing, and paging well enough to call it correctly. The remaining gap is routing versus sibling lookup tools, which the description never addresses.

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

Parameters4/5

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

Schema coverage is only 50%, and the description fills the biggest gap: it names the four allowed `kinds` values, the all-kinds default, and how a module is matched, which the schema does not encode (no enums). It also explains `query` as FTS5 syntax. Slightly redundant with the schema's own limit/offset descriptions and the paging sentence ('offset / next_offset') is terse, so not a 5.

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 resource (full-text search of the ESI index) and enumerates exactly what is indexed: device names/PDOs, CoE objects, diagnosis messages, and modules. It does not distinguish itself from similar siblings such as hw_lookup, hw_object, or hw_module, so an agent still has to guess which of these to pick.

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?

Usage is only implied: the tool is for free-text searching and the `kinds` parameter lets you narrow to device/object/diag/module. There is no explicit statement of when to prefer this over hw_lookup or hw_object, nor any exclusion or prerequisite.

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