Skip to main content
Glama

Alerts and routines

routine
Destructive

Set up a routine: a question RoBot answers again by itself, on a schedule (“every morning at 8: how did my games and their rivals do?”) or when something happens (a trigger), with a note to the person’s notifications (and Discord or email if connected). Use it for “every morning”, “each Monday”, “keep me posted”, “tell me when”, “alert me if”. Each run is RoBot answering, on the person’s RoBot usage. Actions: create (name, question, and every or trigger_sql), update (id, and only what changes), pause, resume, delete, restore, run (once now), list. question is asked whole on each run: name the games and what to compare. Times are New York’s. Opens with RoBot: an account RoBot isn’t open on yet gets not_available.

Input Schema

NameRequiredDescriptionDefault
atNoThe time of day in New York as HH:MM (24-hour), for day and week; default 08:00
idNoThe routine’s id (from create or list), for every action but create and list
nameNoA short name in plain words, like "Morning check-in"
everyNoHow often, for a routine on a schedule
actionYes
deliverNoWhere its note goes (default bell)
minutesNoFor every: minutes, 15 to 1440
weekdayNoFor week; default Mon
questionNoWhat RoBot is asked on each run, whole and on its own
trigger_sqlNoFor a trigger: one read-only SQL query over RoTerminal’s research tables, a row for each thing that has happened, its first column that thing’s key, newest first, LIMIT 50 at most
cooldown_hoursNoFor a trigger: the least time between its runs, 0.25 to 168 (default 6)
max_fires_per_dayNoFor a trigger: the most runs in a New York day, 1 to 24 (default 3)
check_every_minutesNoFor a trigger: how often it’s checked, 5 to 1440 (default 15)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, and the description adds real context: delete is paired with restore, there is a 'run (once now)' escape hatch, all times are New York's, and an unopened account yields not_available. However it never says whether delete is permanent or what restore requires, so the destructive story is only partly filled in.

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?

Front-loads the core concept and the signal phrases before the dense 'Actions:' clause, so an agent can triage quickly. It is heavy with parenthetical clauses and run-on sentences, costing some readability, though almost no sentence is pure filler.

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 13-parameter, eight-action mutation tool with no output schema, it covers the essentials: action-to-parameter mapping, timezone, defaults for scheduling, and the not_available error case. It omits what list returns and whether delete is irreversible, which are the remaining gaps.

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 92%, so 3 is the baseline, but the description earns more by mapping parameters to actions (create needs name, question and every or trigger_sql; update takes id plus only what changes) and by stressing that question is asked whole on each run with the games and comparison named. Trigger parameters (cooldown_hours, max_fires_per_day, check_every_minutes) are left to the schema.

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 concrete verb and resource ('Set up a routine: a question RoBot answers again by itself, on a schedule or trigger') and enumerates the eight operations, so an agent can distinguish this scheduling tool from the read-only sibling query tools without opening the schema.

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 explicit trigger phrases ('every morning', 'each Monday', 'keep me posted', 'tell me when', 'alert me if') that map intent to this tool, and notes runs consume the person's RoBot usage. It never states the inverse case (use the plain query siblings for one-off questions), so it stops short of full when/when-not 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.