Skip to main content
Glama

Ask AI

by com.ask-ai-data-connector
OverviewDiscussionsAdmin

update_intervention

TRIGGER: Call WITHOUT asking when an existing intervention's details need correcting — a check date that should move, a note to add, a hypothesis to sharpen, or a threshold watch to attach. Interventions could previously only be created and closed, so a wrong check date stayed wrong and surfaced as due on the wrong day; closing and re-creating is NOT a workaround, because it discards the captured baseline snapshots and the applied date. NOTES APPEND by default with a date stamp, since corrections accumulate — pass notesMode:'replace' only to deliberately overwrite. Verdict and status are not editable here: closing goes through complete_intervention so post-fix snapshots and deltas are captured with it. EXAMPLE: update_intervention({interventionId: '63f81dc3-...', removeCheckDates: ['2026-09-22'], addCheckDates: ['2026-09-25'], notes: 'Moved the check to the 25th — the 22nd fell before the campaign had 14 days of runtime.'}).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesNoNote to record. APPENDED under a date stamp by default, preserving earlier corrections.
watchNoAttach (or with null, clear) a threshold watch evaluated on every get_briefing, so a breach SURFACES instead of being recomputed by hand. Shape: {metric:'orders'|'revenue', windowDays: 1-90, op:'lt'|'lte'|'gt'|'gte', threshold: number, note?: string}. Example: {metric:'orders', windowDays:3, op:'lt', threshold:55}. Windows cover COMPLETE days only (today is excluded), and a window the order sync does not fully cover reports as indeterminate rather than breached.
_offsetNoPagination offset. If a response includes _pagination.hasMore=true, use _offset to fetch the next page.
notesModeNoDefault 'append'. Use 'replace' only when deliberately discarding the existing notes.
checkDatesNoREPLACE the whole check-date set with these ISO dates (YYYY-MM-DD). To move a single date, prefer addCheckDates/removeCheckDates so the others cannot be dropped by accident. Cannot be combined with add/remove.
hypothesisNoCorrect or sharpen why it was expected to work.
descriptionNoCorrect what was changed.
addCheckDatesNoISO dates to ADD, leaving the rest in place. Result is deduped and sorted.
interventionIdYesThe intervention to edit. Ids are per-shop — one from another store will not resolve.
expectedMetricsNoReplace the per-metric expectations, e.g. {orders: {deltaPercent: 10, direction: 'up'}}.
removeCheckDatesNoISO dates to REMOVE, leaving the rest in place. Pair with addCheckDates to move one date.

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?

With no annotations present, the description carries the full burden and does it well. It discloses that notes append by default with a date stamp, that notesMode:'replace' deliberately overwrites, that verdict/status are not editable here, and that close/re-create discards baseline snapshots and the applied date. These are meaningful behavioral traits beyond the schema.

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?

The description is long but every sentence earns its place: trigger condition, historical context, default behavior, exclusions, and a full example. It is front-loaded with the TRIGGER instruction and avoids filler while covering high-complexity semantics.

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 an 11-parameter mutation tool with no annotations and no output schema, the description is remarkably complete. It explains when to invoke, what can and cannot be edited, how notes accumulate, why re-creating is harmful, and gives a concrete example. Nothing essential to correct invocation is missing.

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 schema already documents all parameters. The description adds value by giving a complete invocation example, clarifying default notes behavior, and reinforcing the relationship between addCheckDates/removeCheckDates vs checkDates. It does not introduce new meaning for every parameter but adds enough context to exceed the baseline.

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 description names a specific verb and resource ('update an existing intervention's details') and lists concrete correction cases: moving check dates, adding notes, sharpening a hypothesis, attaching a threshold watch. It also distinguishes itself from complete_intervention, making it clear what this tool is for and what it is not.

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 explicitly says when to call it ('when an existing intervention's details need correcting') and when not to ('Verdict and status are not editable here: closing goes through complete_intervention'). It also warns that closing and re-creating is NOT a workaround due to data loss, giving an agent concrete decision guidance.

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

All Ask AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources