Skip to main content
Glama

Samuelz® Policy

Unternehmensänderung freigeben

show_company_profile_approval
Read-only

After an explicit company-profile change request, use the exact read revision and patch to show normalized before/after values in the human Owner card. No save on load. Only its Freigeben click writes. Never call confirm_company_profile from the model, expose hidden approval metadata, or infer approval from chat text. No host UI means no write; use the existing settings page.

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": {
      "expectedRevision": "<expectedRevision>",
      "patch": "<patch>"
    },
    "name": "show_company_profile_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
patchYes
expectedRevisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true, and the description explains exactly why that holds and where the boundary is: no save on load, only the human's Freigeben click writes. It also discloses constraints an agent cannot see in structured fields, such as not inferring approval from chat text and not exposing hidden approval metadata. Nothing here contradicts the read-only annotation.

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?

Four sentences, all carrying information, with the safety-critical constraints front-loaded. Slight redundancy between 'No save on load' and 'Only its Freigeben click writes', and the actual purpose arrives after the precondition rather than leading.

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 two-parameter tool with a nested patch object and no output schema, the description covers the interaction model, the human-in-the-loop write gate, and the no-UI fallback well. What remains thin is the shape of the returned before/after payload and the failure behavior on a revision mismatch.

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%, so the description carries the burden; it does clarify that expectedRevision must be the exact revision previously read (implying optimistic concurrency) and that patch is the change payload whose values are normalized. It says nothing about the 64-hex-character pattern, the ten patch fields with maxLength constraints, additionalProperties=false, or whether patch is partial or full. Useful but not compensating for the coverage gap.

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 states a concrete action: render normalized before/after values of a company-profile change into a human Owner approval card, driven by a read revision and patch. It implicitly separates itself from confirm_company_profile by forbidding the model from calling that sibling. The only mild ambiguity is that the rendering/UI nature of the tool is conveyed indirectly ('human Owner card') rather than stated outright.

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

Usage Guidelines5/5

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

It gives an explicit trigger ('After an explicit company-profile change request'), the exact inputs to use ('the exact read revision and patch'), an explicit exclusion ('Never call confirm_company_profile from the model'), and a fallback condition ('No host UI means no write; use the existing settings page'). When-to-use, when-not-to-use, and the alternative path are all covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources