Galley Render

Publish a new template version

update_template

Publish a new immutable version of an existing template. Versions are never edited in place: invoice@2 keeps rendering exactly as it did, and anything pinned to it is unaffected. Renders cached against the old version stay valid, and the new version starts with a cold cache. engine, schema, options and example are inherited from the previous version unless you send them, so a source-only change needs only template and source. Free.

Input Schema

TableJSON Schema

Name	Required	Description
`engine`	No	Engine for the new version. Inherited from the previous version when omitted.
`schema`	No	JSON Schema for the `data` payload. Inherited from the previous version when omitted — send `{}` only if you really want a version that validates nothing.
`source`	Yes	One self-contained HTML document with inline CSS and Liquid expressions (`{{ customer.name }}`, `{% for line in line_items %}`). No file includes: everything the render needs must be in this string, or at a public https URL. Two extra filters ship by default: `money` and `date_medium`. For a PDF, use `@page { size: Letter; margin: 18mm }` to control pagination.
`example`	No	A payload that renders correctly under the new version. Inherited when omitted.
`message`	No	Change note for this version, like a commit message.
`options`	No	Default render options. Inherited from the previous version when omitted.
`template`	Yes	Name of an existing template. A new immutable version is published; earlier versions keep rendering, so anything pinned to `name@2` is unaffected.
`description`	No	Replaces the template description.
`expected_pages`	No	How many PDF pages a typical payload renders. Inherited from the previous version when omitted. This is the estimate the free tier and the spend cap are checked against before the render starts, so a template that runs to several pages must say so or a render that cannot fit the allowance will be started and then go over. It is not a limit: the render is billed on the pages it actually produced.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (which only mark it as non-read-only, non-destructive, and open-world), the description discloses key behavioral traits: immutability, cache behavior (old cache remains valid, new version starts cold), inheritance rules for optional fields, and that the operation is free. This is substantive context an agent needs.

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?

Two sentences, both dense with information. The first sentence states the core purpose and immutability; the second covers cache, inheritance, and minimal usage. No filler or repetition of schema content.

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 publish operation with no output schema, the description covers the critical behaviors (immutability, cache, inheritance, cost) and the schema documents all parameters thoroughly. The only minor gap is the absence of any mention of what the response contains or what happens on invalid template names, but these are not blockers for correctly invoking the tool.

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 baseline is 3. The description adds value beyond the schema by summarizing the inheritance pattern (engine, schema, options, example are inherited) and showing how that reduces the required parameter set. It does not add per-parameter details beyond schema, but the combined guidance is helpful.

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 states a specific verb ('Publish') and resource ('new immutable version of an existing template'), making it immediately distinct from create_template. It also clarifies the versioning model ('invoice@2 keeps rendering exactly as it did'), which eliminates ambiguity about what the tool does.

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?

The description clearly implies when to use this tool (for existing templates) and gives practical guidance on minimal calls ('a source-only change needs only template and source'). However, it does not explicitly name alternatives or state when not to use it, such as 'use create_template for a new template'.

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

All Galley Render 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?