Skip to main content
Glama

Open a file (costs credits)

open_file
Idempotent

Opens a project, company or city file and spends its price in credits. Only after the person agreed to the price from quote_file. Opening the same file again is free. Returns names, companies, contacts, facts with sources and signals.

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": {
      "typ": "<typ>",
      "ref": "<ref>",
      "confirm": "<confirm>"
    },
    "name": "open_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYes10 character id from find_projects, new_signals or my_files
typYesp = project file, co = company file, c = city file
confirmYesMust be true: the person agreed to spend the credits

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare non-read-only, idempotent and non-destructive, and the description adds real context beyond that: a credit cost is incurred, prior human consent is mandatory, and repeat opens are free. It also sketches the payload (names, companies, contacts, facts with sources and signals), though it says nothing about failure behavior when confirm is false or credits are insufficient.

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

Conciseness5/5

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

Three tight sentences, front-loaded with the action and its cost, then the consent gate, then the free-repeat and return-value notes. No filler and nothing that could be cut without losing meaning.

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 three-required-parameter mutation-ish tool with no output schema, the description covers cost, consent, idempotency and return contents — enough to call it correctly. The only gap is error/precondition failure handling, which is minor given the explicit confirm flag.

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%, so ref, typ and confirm are already fully documented including the enum meanings. The description only reinforces confirm indirectly via 'only after the person agreed to the price' and adds no format or edge-case detail beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (opens) plus the exact resource set (project, company or city file) and adds the defining consequence: it spends the file's price in credits. That cost-bearing framing separates it cleanly from the free-read siblings get_file and my_files, and it names quote_file as the pricing prerequisite.

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?

Gives an explicit precondition — call only after the person agreed to the price from quote_file — and clarifies the repeat-use case (opening the same file again is free). It stops short of naming get_file as the alternative for a free/preview read, so the when-not-to-use side is only implied.

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