Skip to main content
Glama

AINDEX

Set up an agent's checks on this computer

schedule_checks

For an agent that thinks with this app: makes a key that can only run this one agent's checks and gives the commands that install them on this computer (a script in ~/.aindex and a crontab line). Show the person what will be installed and ask before running it; it needs to run outside any sandbox. The key goes straight from AINDEX to a file here, never into this chat. Needs this chat connected with Run my agents.

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": {
      "agent": "<agent>"
    },
    "name": "schedule_checks"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already flag readOnlyHint=false and openWorldHint=true, but the description still adds meaningful behavior: the key is scoped to one agent only, a file is written to ~/.aindex plus a crontab entry, and the key bypasses the chat entirely. That is genuine side-effect and secret-handling disclosure beyond the structured fields. It does not say whether re-running replaces or duplicates the existing crontab line, which matters given idempotentHint=false.

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 is front-loaded, followed by safety instructions and prerequisites in a logical order, with no filler sentences. The prose is dense and slightly run-on, which costs a little readability but not substance.

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 side-effecting setup tool with no output schema, it covers the important unknowns: what gets installed, where, that it needs elevated/unsandboxed execution, and how the secret is handled. The shape of the returned commands and behavior on repeat invocation are the remaining gaps.

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?

There is one required parameter with 0% schema description coverage, so the description carries the burden. It implies the agent identifies which agent's checks are being installed ('this one agent's checks'), but never names the parameter or explains its format; the regex pattern in the schema is the only format signal. Partial compensation, not full.

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 set (mint a scoped key, produce install commands) and the resource (this agent's checks on this computer), including what the installed artifacts are: a script in ~/.aindex and a crontab line. It is clearly distinct from siblings like start_agent_check or set_agent_mode. It loses a point only because the opening clause 'For an agent that thinks with this app' delays the actual verb.

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 real preconditions: the chat must be connected with 'Run my agents', and the install must run outside a sandbox. It also prescribes the interaction pattern ('show the person what will be installed and ask before running it'). It stops short of naming when NOT to use it or which sibling handles check execution versus setup, so no explicit alternative routing.

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.

Resources