Skip to main content
Glama
netlify

Netlify MCP Server

Official
by netlify

netlify-deploy-services-updater

Deploys a site directory to Netlify by providing the project path and site ID, updating your live site with your local code.

Instructions

Select and run one of the following Netlify write operations deploy-site

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selectSchemaYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / selectSchema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / selectSchema / properties / params / additionalProperties
      Removed value: -false
  2. Addedv1.0.0

TDQS

C2.5/5.0
Behavior2/5

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

`readOnlyHint: false` already marks the tool as mutating, and the description's 'write operations' only restates that. It does not disclose that deployment updates the live Netlify site, requires a valid `siteId`, or may fail if the deploy directory is incorrect. No destructive consequences or auth requirements are described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, but it spends words on filler ('Select and run one of the following') and places the actual operation at the end. It is brief but not cleanly informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating deployment tool with no output schema and only a readOnlyHint annotation, the description is under-specified: no workflow, preconditions, return status, or relationship to linking existing sites is provided. The schema's `siteId` warning helps, but the tool description itself leaves important operational context to be inferred.

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?

The tool description adds no parameter guidance and never references `selectSchema`, `params`, `deployDirectory`, or `siteId`. However, the nested schema compensates with detailed descriptions, including the strong warning not to assume a new site, so the missing parameter text is not a fatal gap despite the 0% schema coverage signal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact operation (`deploy-site`) and labels it a Netlify write, so an agent can infer the tool deploys a site. However, it never states what deployment actually does and uses generic dispatcher language ('Select and run one of the following') that obscures the single available operation. It does not actively distinguish this from sibling updater/reader tools beyond the operation name.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool instead of `netlify-deploy-services-reader` or other sibling updaters, and no preconditions, exclusions, or alternative tools are mentioned. The only hint is the word 'write,' which is already implied by the tool name and annotations.

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