Skip to main content
Glama

Plures

Add your own check to the agent map

add_check

Puts a person in front of any step of an app's agent map, including steps the map didn't flag. It goes live at once (tasks the agent sends with its category follow it) and stays when the app is mapped again. Call get_agent_map first to see the step ids. Ask the user before adding one.

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": {
      "at": "<at>",
      "title": "<title>",
      "question": "<question>",
      "options": "<options>"
    },
    "name": "add_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
atYesThe id of the step (node) the check sits at
appNoThe app id. Default: PLURES_APP, then the default app
whyNoOne sentence on what goes wrong without a person
showNoThe fields of the agent's data people see
routeNoverifiers (default) or team, for the developer's own people
titleYesA short name, like Check emails to customers. The category is made from it
optionsYes2 to 8 answers, the one that lets the agent go ahead first
questionYesWhat people decide, answerable from what they're shown

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that the check goes live immediately, that agent-sent tasks carrying its category then follow it, and that it survives re-mapping of the app. It also imposes a human-confirmation step. It does not describe permissions or how a check is later removed, which keeps it off a 5.

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?

Three short sentences, each carrying a distinct fact: what it does, how it behaves once created, and the two procedural prerequisites. The prerequisite ordering is front-loaded and nothing is padded.

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 an 8-parameter write tool with no output schema, the description covers the critical unknowns: immediate activation, persistence across re-mapping, upstream dependency on get_agent_map, and the need for user consent. Only the absence of any removal or permission context is a gap.

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 every parameter is already documented in the schema, including the 2-8 options ordering and the route enum. The description adds only one small relationship, that the title generates the category, so baseline 3 is appropriate.

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 concrete verb and object: putting a person in front of any step of an app's agent map, explicitly including steps the map did not flag. That scope note separates it from map-generated checks, though it never names a sibling such as set_check to sharpen the boundary.

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 two explicit operating conditions: call get_agent_map first for step ids, and ask the user before adding one. It stops short of saying when to prefer this over set_check or add_standards_rule, so the alternative-selection guidance is implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.