Skip to main content
Glama

tia_analisis

Read-only

Analyzes Siemens TIA Portal V17 programs to locate operand references, callers, call trees, uncalled blocks, and faults like double coils, shared instances, overlapping addresses, and orphan DBs.

Instructions

Diagnóstico del programa (lee todos los bloques; KOP/FUP por XML y SCL por su fuente).

  • referencias: dónde se lee/escribe operando ("Motor", #Marcha, "DB_X".campo) [bloque filtra].

  • llamadores: quién llama a bloque y con qué instancia.

  • arbol: árbol de llamadas desde los OB (o desde bloque).

  • no_llamados: FB/FC que ningún OB ejecuta.

  • diagnostico: doble bobina, set sin reset, instancias compartidas, marcas leídas sin escribir, direcciones solapadas, bloques no llamados, inconsistentes, DB huérfanos, tags sin uso.

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": {
      "action": "<action>"
    },
    "name": "tia_analisis"
  }
}

Input Schema

NameRequiredDescriptionDefault
plcNo
actionYes
bloqueNo
limiteNo
operandoNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.0.0

TDQS

B3.4/5.0
Behavior3/5

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

The description adds real context beyond the annotations: it reads all blocks and parses KOP/FUP via XML and SCL via source, which hints at thoroughness and cost. Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. However, nothing is said about runtime cost of the broad diagnostic sweep, error behavior if a block is missing, or whether `plc` defaults to the active project.

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?

One lead sentence plus five terse bullets, front-loaded with the overall purpose and each bullet scoped to one action. Every bullet corresponds to a real enum value and no filler text is present; only the parenthetical filter note is slightly compressed.

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, so return formats need not be described, and the mode enumeration gives the agent enough to pick an action. For a five-parameter multi-mode tool with zero schema description coverage, the missing semantics for `plc` and `limite` and the lack of per-action parameter requirements leave a real gap.

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 0% for five parameters, so the description carries the burden and only partly pays it: it explains `operando` with concrete syntax examples ("Motor", #Marcha, "DB_X".campo) and clarifies that `bloque` filters referencias and is the target/root for llamadores and arbol — genuinely useful. `plc` and `limite` (default 200) are never mentioned, and it does not say which parameters each action requires or ignores.

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 opening line states a specific verb+resource ('Diagnóstico del programa') and the bullet list names five distinct analyses (referencias, llamadores, arbol, no_llamados, diagnostico) that map onto the action enum, so an agent can tell what each mode does. It does not contrast itself with siblings like tia_bloques or tia_conocimiento, so differentiation must be inferred from the action names alone.

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?

The bullets imply when each action applies (e.g. arbol for call hierarchy, no_llamados for dead code), but no explicit when-to-use/when-not guidance or alternatives are given. There is no statement of prerequisites such as whether a project must be open or a session established, nor which sibling to use for non-analytical tasks.

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