Skip to main content
Glama

Calcgrid

by com.tttkmbb
OverviewDiscussionsAdmin

Search calculators

search_calculators
Read-onlyIdempotent

Use this when a user needs a deterministic calculation but none of the dedicated tools clearly matches and the calculator_id is unknown. Search 737 calculators from the complete task in English or Chinese, then call run_calculator with the top matching calculator_id and returned input_hints. Do not use this for trivial arithmetic, live data, writing tasks, or when a dedicated typed tool already matches. This tool only discovers; it does not calculate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYesThe complete user task, including known values and units; for example 'compound interest on 15000 at 4.8% monthly for 12 years'.
categoryNoOptional category id to restrict results.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
linksNo
resultYes
requestNo
successYes
timestampYes
next_actionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / query / description
      Previous value: -"Free-text query, e.g. 'compound interest' or 'body fat'."New value: +"The complete user task, including known values and units; for example 'compound interest on 15000 at 4.8% monthly for 12 years'."
    • addedInput schema / properties / query / examples
      Added value: +[
+  "compound interest on 15000 at 4.8% monthly for 12 years"
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Read-only catalogue or schema result used to select a calculation tool.",
+  "properties": {
+    "links": {
+      "type": "object"
+    },
+    "next_actions": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "request": {
+      "type": "object"
+    },
+    "result": {
+      "type": "object"
+    },
+    "success": {
+      "const": true,
+      "type": "boolean"
+    },
+    "timestamp": {
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "required": [
+    "success",
+    "result",
+    "timestamp"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, openWorldHint=false, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond that: it operates only as a discovery step, searches across 737 calculators in English or Chinese, and returns calculator_id plus input_hints. No gates or rate limits are mentioned, but the safety profile is well covered.

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 sentences, front-loaded with the primary use case, then the mechanism, exclusions, and a final scope reminder. Every sentence adds distinct value with no repetition or filler.

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 read-only discovery tool with a full output schema and strong annotations, the description covers purpose, usage boundaries, search scope, language support, and the follow-up call. Return values need not be explained because an output schema exists. Nothing essential is missing.

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 67%, and the schema already defines query with an example and category as an optional restriction. The description reinforces that query should include the complete user task and language, but it does not explain the limit parameter or add syntax beyond what the schema provides. Baseline 3 is appropriate given the schema carries most of the parameter meaning.

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 ('Search') and resource ('737 calculators') and explicitly distinguishes itself from siblings by saying it only discovers and does not calculate. It also names the follow-up tool (run_calculator), so an agent can tell exactly what this tool is for versus the dedicated typed calculators.

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?

Explicitly states when to use it ('none of the dedicated tools clearly matches and the calculator_id is unknown') and when not to use it ('trivial arithmetic, live data, writing tasks, or when a dedicated typed tool already matches'). It also names the next action (call run_calculator), leaving no ambiguity about routing.

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

All Calcgrid toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources