Skip to main content
Glama

recipebooq

by com.recipebooq
OverviewDiscussionsAdmin

Update supplied components

update_components
Read-onlyIdempotent

Needs a subscription. Reads the project's .opointo/files.json and returns only the opointo-supplied files that changed since export, so it works months later with no share code. Never touches the customer's own screens, and flags the rare change that needs a code edit rather than a copy.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
currentNoonly when a split-unverified blocker asks: each named file's hash, from its command
manifestYesthe parsed .opointo/files.json (the object or its files array)
acceptSplitNoonly once the customer agreed: the paths split-customer-edited blockers name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / acceptSplit / description
      Previous value: -"only after the customer agreed to replace a file they edited: the paths named by `split-customer-edited` blockers"New value: +"only once the customer agreed: the paths split-customer-edited blockers name"
    • changedInput schema / properties / current / description
      Previous value: -"only when a `split-unverified` blocker asks for it: the hash of each named file on disk, from the command the blocker gives"New value: +"only when a split-unverified blocker asks: each named file's hash, from its command"
    • changedInput schema / properties / manifest / description
      Previous value: -"the parsed contents of .opointo/files.json from the project root (the whole object, or just its `files` array)"New value: +"the parsed .opointo/files.json (the object or its files array)"
  2. Changed1 schema field changed
    • changedInput schema / properties / manifest / description
      Previous value: -"the parsed contents of .recipebooq/files.json from the project root (the whole object, or just its `files` array)"New value: +"the parsed contents of .opointo/files.json from the project root (the whole object, or just its `files` array)"
  3. Changed2 schema fields changed
    • addedInput schema / properties / acceptSplit
      Added value: +{
+  "description": "only after the customer agreed to replace a file they edited: the paths named by `split-customer-edited` blockers",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / current
      Added value: +{
+  "description": "only when a `split-unverified` blocker asks for it: the hash of each named file on disk, from the command the blocker gives",
+  "items": {
+    "properties": {
+      "missing": {
+        "type": "boolean"
+      },
+      "path": {
+        "type": "string"
+      },
+      "sha": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "path"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
  4. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive, and the description resolves the tension with the 'update' name by clarifying it only reads and returns changed files. It adds useful context beyond annotations: subscription requirement and the guarantee that it 'never touches the customer's own screens.'

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?

Two dense sentences with essentially no filler, though the leading 'Needs a subscription' puts a precondition ahead of the primary purpose rather than front-loading what the tool does.

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 read-only tool with full schema coverage and clear annotations, the description covers the key behavior including what it returns and what it avoids touching. Return-format detail is light, but annotations and schema carry the rest.

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 schema already documents manifest, current, and acceptSplit in detail. The description adds only an oblique reference to changes needing a code edit and does not expand on any parameter, so the baseline 3 applies.

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?

The description gives a specific action set — reads the project's .opointo/files.json and returns only opointo-supplied files that changed since export — which is far more concrete than the ambiguous name 'update_components'. However, it does not explicitly distinguish itself from siblings such as install_component or get_component, so an agent must infer the boundary.

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?

A precondition is stated ('Needs a subscription') and the description implies the re-export/months-later scenario, but it never says when to choose this over install_component, get_component, or check_snippet. Usage is implied rather than contrasted with alternatives.

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

All recipebooq 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