Skip to main content
Glama

call

Runs a catalog-defined session tool with an arguments object, enabling coding agents to act on live app screens and capture repeatable test lines.

Instructions

Run one tool of a session by name, with its arguments as an object: call {tool: "tap", args: {target: "n42"}, session: ""}. The session's catalog (from open_session or tools) names the tools and their arguments. Actions report what changed on screen and the test line that repeats them; node ids are valid only for the newest observation.

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": {
      "tool": "<tool>"
    },
    "name": "call"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoThe tool's arguments; omit for a tool without any
toolYesA catalog tool name, e.g. "observe", "tap", "locate", "screenshot"
sessionNoSession id from open_session; may be omitted only while one session is open

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.23.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description carries most of the behavioral burden and does add real value: actions report "what changed on screen and the test line that repeats them," and the critical caveat that "node ids are valid only for the newest observation." It does not cover failure behavior for unknown tool names or invalid args, so it stops short of full transparency.

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?

Three sentences, front-loaded with the action and example; every clause carries information. The final clause about node-id freshness is slightly compressed and would read better as its own sentence, 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 three-parameter dispatcher with a free-form nested args object and no output schema, the definition supplies the prerequisite (catalog from open_session/tools), the call shape, and a sketch of what results look like (screen changes plus the repeating test line). What is missing is error/validation behavior and how to recover from a stale node id.

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 100%, so baseline is 3, but the description goes beyond it by showing the exact shape `{tool: "tap", args: {target: "n42"}, session: "<id>"}` and by explaining that args mirrors the target tool's own argument object. That resolves the ambiguity of a free-form nested object better than the schema text alone.

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?

The description states a specific verb and resource — "Run one tool of a session by name, with its arguments as an object" — and immediately grounds it with a concrete payload example showing how tool/args/session compose. This is clearly a generic dispatcher, distinguishable from the session-management siblings (open_session, tools, close_session) and from run_tests.

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?

It tells the agent where the valid tool names come from ("The session's catalog (from open_session or tools)") and ties the tool to an open session, which is genuine routing context. However, it never states when to prefer this dispatcher over run_tests, or what happens if a catalog name is wrong, so the caller must infer the boundary.

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