Skip to main content
Glama

call_cell

Run a verified, SHA-locked calculation cell by exact name with required inputs, either inline or from a JSON file; returns an honest status instead of guessing.

Instructions

Run a locked cell found with find_cell (use its exact name; do not guess names). Use the cell's required input keys exactly, as in its input example. Pass its input either inline as input or, for large data, as input_file (path to a JSON file holding the input object) so the data need not be retyped. Returns status ok (verified result), not_available, or invalid_input. Never invents a result. If refused, the reply's how_to_fix shows the exact input to send again.

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": {
      "cell": "<cell>"
    },
    "name": "call_cell"
  }
}

Input Schema

NameRequiredDescriptionDefault
cellYes
inputNo
input_fileNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.6

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it enumerates the outcome states (ok, not_available, invalid_input), asserts the tool never fabricates a result, and describes a recovery path via how_to_fix on refusal. What is missing is whether running a cell has side effects or is a pure computation, and any permission requirements.

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?

Four tight sentences, front-loaded with the prerequisite and the naming rule, then the input-delivery options, then the return contract. Every sentence adds information an agent needs and nothing is repeated from the schema or title.

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?

Given no annotations and no output schema, the description covers return statuses, the anti-hallucination guarantee, and the error-recovery route, plus meaning for all three parameters. It leaves undefined what a 'locked cell' is in terms of side effects and whether both input and input_file may be sent together.

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 0%, so the description must supply meaning, and it does for all three: cell is the exact name from find_cell, input is the inline object keyed to the cell's required input keys, and input_file is a path to a JSON file holding that same object. The 'either/or' phrasing also implies mutual exclusivity the schema does not encode. It does not state precedence if both are supplied.

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 ('Run a locked cell') and anchors it to the sibling that produces the name ('found with find_cell'). An agent can tell this executes a cell rather than discovering one. It does not distinguish itself from request_cell, which is the remaining ambiguity.

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 clear preconditions: obtain the cell via find_cell, use its exact name, do not guess names. It also states the inline-vs-file choice for supplying input. It stops short of saying when to prefer this over request_cell or list_cells.

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