Skip to main content
Glama

find_cell

Find verified calculation cells for rule-based numbers like wages, rates, margins, or percentiles. Returns matching cells with required inputs and examples, or an empty list when none fit.

Instructions

Call this first whenever the user asks for a number worked out by rules: wages, salary, rates, growth, margins, prices, percentiles, calories, currency, leave days and similar. Verified cells give the exact checked answer, and small models get these wrong when computing alone. State the need in plain words. Returns the cells that fit, each with its required inputs and an input example, or an empty list when nothing fits.

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": {
      "need": "<need>"
    },
    "name": "find_cell"
  }
}

Input Schema

NameRequiredDescriptionDefault
needYesWhat you need computed, in plain words (Korean or English).
wordsNoOptional: 3-6 standard names for the calculation (e.g. 연평균 성장률, 이동평균). They are searched too, which helps the hub find a cell when the request is worded unusually.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.6

TDQS

A4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the return shape: matching cells with required inputs and an input example, or an empty list on no match. It also explains the motivation (verified, checked answers versus small models computing alone), which tells the agent why results should be trusted. It says nothing about source, permissions, rate limits, or what happens after an empty result.

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?

Front-loaded with the imperative 'Call this first whenever...' so the decision rule lands in the opening clause, and the return behavior is closed out cleanly at the end. The long domain enumeration is bulky but functional for keyword matching. 'State the need in plain words' mildly duplicates the schema description and could be cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, no-annotation lookup tool with no output schema, the description covers everything an agent needs: the trigger condition, the input phrasing expectation, the return payload structure, and the empty-result case. Nothing essential to a correct first call is missing, and since no output schema exists, spelling out the return format here is exactly the right allocation.

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 100%, so both parameters are already documented with their own descriptions and language guidance. The description reinforces the 'need' parameter with 'State the need in plain words' but adds no new meaning, and it never mentions the optional 'words' parameter or when supplying standard names materially improves recall. Baseline 3 is appropriate when the schema does the work.

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 retrieval action ('Call this first', 'Returns the cells that fit') over a specific resource: verified computation cells keyed to a need. The phrase 'call this first' plus 'returns the cells' implies lookup, not execution, which implicitly separates it from call_cell, but it never names the siblings that would execute or request a cell. An agent can infer the role, though not with the crispness of an explicit contrast.

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?

Strong trigger guidance: use whenever the user asks for a number produced by rules, followed by a long, concrete example list (wages, rates, growth, margins, percentiles, calories, currency, leave days). The 'call this first' wording also establishes ordering relative to follow-on tools. It lacks an explicit when-not condition (e.g., what to do when nothing fits beyond returning an empty list) and never names alternatives.

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