Skip to main content
Glama
eMCP for Evolution CMS

eMCP for Evolution CMS

Official

Measure Tool

amount.measure

Measures disk space usage for an entire mount, a rule's remote or local folder, or a sub-folder; runs in the background and returns a run ID to poll for results.

Instructions

Count how much space something uses ("how much does the S3 mount use"). Read-only but slow, so it runs in the background and returns a run uuid: poll amount.status until finished, the result is its usage. Give mount for a whole mount (a shared site mount needs an administrator; other managers measure their own rule), or rule for a rule's remote folder, or rule + local=true for its local folder. path narrows to a sub-folder.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "amount.measure"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoSub-folder to count, e.g. "Backups" (default: everything)
ruleNoRule uuid from amount.rules
localNoWith `rule`: count the local site folder instead of the remote one
mountNoMount uuid or name (when no rule is given)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations are empty, so the description carries the full burden and does so well: it discloses read-only-ness, that the operation is slow and therefore asynchronous, that the immediate return is a run uuid rather than the answer, and that the caller must poll amount.status until `finished` and read `usage`. The administrator requirement for shared site mounts is exactly the kind of authorization context an agent cannot infer from schema alone.

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, async contract, and parameter modes are correctly front-loaded with no filler sentences. However, the three alternative targeting modes are crammed into one dense run-on sentence that must be parsed carefully; a short structured breakdown would read faster without adding length.

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 zero-required-parameter, no-output-schema tool that triggers slow background work, the definition covers everything needed: how to know it succeeded (poll amount.status to `finished`), where the answer lives (`usage`), and how to choose among four parameters. Nothing material is left for the agent to guess.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds genuine semantics the schema cannot express: that `mount` applies only when no `rule` is given, that `local` is meaningless without `rule`, that `rule` takes a uuid sourced from amount.rules, and that `path` narrows rather than replaces the target. These combination and precedence rules are the real value.

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 definition opens with a specific verb and resource ("Count how much space something uses") plus a concrete example query, and it distinguishes itself from the polling sibling by naming amount.status as the follow-up step. An agent immediately knows this initiates a disk-usage measurement rather than browsing files or listing mounts.

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?

It enumerates the mutually exclusive invocation modes with their conditions: `mount` for a whole mount, `rule` for a rule's remote folder, `rule` + local=true for the local folder, and `path` to narrow. It also flags the permission case (a shared site mount needs an administrator; other managers measure their own `rule`), leaving no ambiguity about which parameters to combine.

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