Skip to main content
Glama
Sign In

ToolsMonk tool catalog

by com.toolsmonk
OverviewDiscussionsAdmin

Run a ToolsMonk tool

run_tool
Read-only

Run a ToolsMonk tool and return its result. Works for business, finance and student calculators, text, developer and document utilities; web tools (seo-checker, site-audit, website-speed-test); regex-tester and regex-generator; AI tools (free-ai-humanizer-tool, ai-image-generator, ai-pdf-summarizer, resume-maker); and light file tools (merge, split, rotate, number or watermark a PDF, resize, convert or compress an image, and more), which take a file the user attached (pass it in the top-level files parameter) or a public https fileUrl (max 10 MB), and return a download link valid for one hour. These have their own small daily limits per account. See list_runnable_tools, or check mcp.runnable from get_tool. Pass the tool slug and an input object matching that tool's input schema. Heavy file tools (OCR, Office conversion, background removal, editors) cannot run here; for those the error message gives the URL to open. Inputs and outputs are not stored.

Input Schema

NameRequiredDescriptionDefault
slugYesThe tool slug, e.g. "roi-calculator-biz" or "json-formatter".
filesNoFiles the user attached in the conversation, for file tools. Fills the tool's `fileUrl` (first file) or `fileUrls` (all files) when `input` does not give one. Max 10 MB each.
inputNoArguments for the tool, as described by its input schema.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / slug / description
      Previous value: -"The tool slug, e.g. \"bmi-calculator\" or \"json-formatter\"."New value: +"The tool slug, e.g. \"roi-calculator-biz\" or \"json-formatter\"."
  2. Changed1 schema field changed
    • addedInput schema / properties / files
      Added value: +{
+  "description": "Files the user attached in the conversation, for file tools. Fills the tool's `fileUrl` (first file) or `fileUrls` (all files) when `input` does not give one. Max 10 MB each.",
+  "items": {
+    "properties": {
+      "download_url": {
+        "description": "Temporary link to the attached file.",
+        "type": "string"
+      },
+      "file_id": {
+        "description": "The assistant's id for the file.",
+        "type": "string"
+      },
+      "file_name": {
+        "type": "string"
+      },
+      "mime_type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "download_url",
+      "file_id"
+    ],
+    "type": "object"
+  },
+  "maxItems": 10,
+  "type": "array"
+}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses per-account daily limits, a one-hour download-link lifetime, a 10 MB per-file cap, the fallback behaviour for unsupported heavy tools (error text carries a URL), the files-vs-fileUrl precedence, and that inputs/outputs are not stored. That last point is what reconciles running mutating sub-tools with readOnlyHint=true.

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?

Purpose and return behaviour are front-loaded, and the middle enumeration earns its length by letting an agent pattern-match its target tool. The long parenthetical lists (resume-maker, ai-pdf-summarizer, site-audit) are close to bloat and could be trimmed to category names without losing selectivity.

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 dispatcher with a free-form nested `input` and no output schema, the description covers dispatch mechanics, file handling, limits and the escape hatch for unsupported tools. The only soft spot is that 'return its result' never characterizes the response shape, which matters because results differ per slug.

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 the baseline applies, but the description adds real semantics: `input` must match the target tool's own input schema, and top-level `files` is only the fallback when `input` does not already supply fileUrl/fileUrls. It does not cover slug formatting rules or maxItems beyond what the schema states.

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 and resource ('Run a ToolsMonk tool and return its result') and then enumerates the exact tool families it dispatches to, so an agent can tell instantly whether its target calculator, regex tool, AI tool or light file tool belongs here. It also separates itself from the discovery siblings by naming list_runnable_tools and get_tool as the lookup path.

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 a clear when-to-use path (look up the slug via list_runnable_tools or `mcp.runnable` from get_tool, then call this) and an explicit exclusion: heavy file tools (OCR, Office conversion, background removal, editors) cannot run here and surface a URL instead. It does not explicitly contrast with search_tools/list_tools for other discovery needs, so it stops short of a full when/when-not map.

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

All ToolsMonk tool catalog toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources