Capable

Update quote

update_quote

DestructiveIdempotent

Update a quote: change its status (draft → sent → accepted / lost), link an opportunity, or replace its line items. When you pass lines, the SERVER re-prices from the catalog (you never pass a price) and replaces the whole line set; the quote total is recomputed. Catalog products live on the product object and price from unit_price_cents (integer CENTS) + pricing_mode — per_unit multiplies by quantity, flat charges once (missing/unknown pricing_mode resolves to flat; a flat line with quantity > 1 is flagged). Discounts are by PERCENT only (per-line discount_pct on a line and/or a quote-level discount_pct) and apply when you re-price (pass lines to change a discount). Status/opportunity-only edits don't re-price. Status is exactly draft, sent, accepted, or lost — a quote is a pre-commit artifact (invoicing and contracts happen elsewhere). Returns the updated quote, its priced lines, and any flags.

When to use: When a quote needs to change — move it from draft to sent, mark it accepted or lost, link an opportunity, or swap its items. Passing new items re-prices from the catalog and recomputes the total; you never pass a price.

Example: Mark Acme's quote as sent, and add 5 more units.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	A uuid.
`name`	No	New display name for the quote; replaces the stored header name.
`lines`	No	At least one item.
`notes`	No	New free-text notes for the quote header; replaces the stored notes and never affects pricing.
`status`	No	One of: draft \| sent \| accepted \| lost.
`valid_until`	No	Must match /^\d{4}-\d{2}-\d{2}$/.
`discount_pct`	No	A number from 0 to 100.
`opportunity_id`	No	Opportunity to link the quote to (must exist in this workspace); null clears the link, omitting leaves it unchanged.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`note`	No
`quote`	No
`updated`	No
`guidance`	No
`repriced`	No
`line_items`	No
`mixed_cadence`	No
`missing_objects`	No
`tier_validations`	No
`annualized_total_cents`	No
`pricing_mode_validations`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond annotations by disclosing that the SERVER re-prices from the catalog (client never passes a price), replaces the entire line set, recomputes the total, and that status/opportunity-only edits don't re-price. It also details pricing_mode resolution and that discounts are percent-only, all of which an agent needs to call this destructive-but-idempotent mutation correctly.

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?

Dense and front-loaded with the operation summary first, then behavioral detail, then when-to-use and example. It is long, and 'you never pass a price' is repeated across two sections, a minor redundancy that keeps it from a 5.

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 8-parameter mutation with a rich output schema and full annotation coverage, the description supplies everything needed: re-pricing behavior, discount mechanics, status enum semantics, and the return shape (quote, priced lines, flags). Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description substantially enriches semantics: it explains how `lines` are re-priced and that they replace the whole set, how `pricing_mode` (per_unit vs flat, unknown→flat) resolves, and that `discount_pct` applies only on re-price. This is meaningfully more than the schema provides.

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 opens with a specific verb+resource ('Update a quote') and enumerates the three distinct operations: status change, opportunity link, and line-item replacement. It clearly distinguishes this from create_quote and from downstream invoicing/contract work.

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?

A dedicated 'When to use' section names the triggering conditions (draft→sent, mark accepted/lost, link opportunity, swap items) and scopes the tool as a pre-commit artifact with invoicing/contracts happening elsewhere. An example anchors the usage.

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

All Capable tools Inspect

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

Need Help?