Skip to main content
Glama
Sign In

HelpWell

by ai.helpwell.app
OverviewDiscussionsAdmin

Update the contact panel layout

update_contact_panel
DestructiveIdempotent

Change the contact panel for the whole team: block order and visibility, the Stripe rows, pinned fields, how many show, header badges and hiding empty fields. Name and details always come first. Only the parts you pass change. Admins only.

Input Schema

NameRequiredDescriptionDefault
limitNoPinned fields shown before "Show all".
badgesNoUp to two field keys shown as chips beside the name.
pinnedNoPinned field keys in order (from get_contact_panel); always shows a dash when empty.
sectionsNoBlocks in order, under the name and details: stripe, fields, conversations, sessions, issues, journeys, enrichment, activity. A block left out is hidden.
hideEmptyNoSkip pinned fields with no value.
stripeRowsNoThe rows the Stripe block shows: plan, status, since (customer since), ltv (lifetime value), price, invoice (last invoice), paid (paid to date), cancellation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / sections / description
      Previous value: -"Sections in order: details, stripe, journeys, enrichment, fields, conversations, activity. A section left out is hidden."New value: +"Blocks in order, under the name and details: stripe, fields, conversations, sessions, issues, journeys, enrichment, activity. A block left out is hidden."
    • addedInput schema / properties / stripeRows
      Added value: +{
+  "description": "The rows the Stripe block shows: plan, status, since (customer since), ltv (lifetime value), price, invoice (last invoice), paid (paid to date), cancellation.",
+  "items": {
+    "enum": [
+      "plan",
+      "status",
+      "since",
+      "ltv",
+      "price",
+      "invoice",
+      "paid",
+      "cancellation"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower; the description still adds meaningful behavior: workspace-wide blast radius, admin permission requirement, partial-merge semantics, and the invariant that name/details always lead the layout. It does not explain reversibility or how to restore a default layout, which is what makes the destructive flag surprising.

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-loaded with the scope and effect in one dense opening clause, followed by high-value constraints ('Name and details always come first', 'Only the parts you pass change', 'Admins only'). The enumeration is a long comma chain but every element maps to a real parameter; little is wasted.

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?

Six all-optional parameters, no output schema, and a workspace-wide mutation — the description covers scope, permissions, and merge behavior, which is what an agent needs to call it safely. Missing only the reset/default path and confirmation of what is returned after the change.

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 the baseline is 3. The description restates the parameter concepts in plain language (block order, Stripe rows, pinned fields, how many show, badges, hiding empty fields) but adds no format, ordering, or validation detail beyond what the schema's own descriptions already carry.

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 specific verb ('Change') plus the resource ('the contact panel') and enumerates exactly what is configurable: block order/visibility, Stripe rows, pinned fields, limit, badges, hide-empty. It is clearly distinguishable from the read-side sibling get_contact_panel, which the pinned parameter description explicitly references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Admins only' and 'for the whole team' give real prerequisites and scope, and 'Only the parts you pass change' implies a partial-update pattern. However, there is no explicit guidance on when to use this versus a per-contact update or when to read the current layout first (get_contact_panel is only mentioned inside the schema, not in the description).

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

All HelpWell 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