Skip to main content
Glama

Publish a folder

publish_dir
Destructive

Publish a folder as a live HTTPS site and get its URL. Requires an index.html at the root, or .md and .pdf files served through the reader.

Instructions

Publishes a folder of static files and returns its URL. The folder needs an index.html at its root, or .md and .pdf files, which are served through the reader.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesAbsolute path of the folder to publish.
siteNoSubdomain or site id to publish over. Omit to create a new site.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe live URL of the published site.
filesYesHow many files the site now serves.
siteIdYesIdentifier of the site, stable across publishes.
subdomainYesThe site's subdomain, which is what `site` accepts.
unchangedYesTrue when every file already matched what the site served, so no new version was published.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "files": {
      +      "description": "How many files the site now serves.",
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "siteId": {
      +      "description": "Identifier of the site, stable across publishes.",
      +      "type": "string"
      +    },
      +    "subdomain": {
      +      "description": "The site's subdomain, which is what `site` accepts.",
      +      "type": "string"
      +    },
      +    "unchanged": {
      +      "description": "True when every file already matched what the site served, so no new version was published.",
      +      "type": "boolean"
      +    },
      +    "url": {
      +      "description": "The live URL of the published site.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "url",
      +    "siteId",
      +    "subdomain",
      +    "files",
      +    "unchanged"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

Adds genuine behavioral context beyond the annotations: the index.html-at-root requirement and the .md/.pdf reader-serving path. However, the annotations flag destructiveHint=true and the description is silent on what publishing over an existing 'site' destroys or replaces, which is exactly the consequence an agent needs before invoking it.

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 efficient sentences with the action and return value front-loaded and the content requirement second. Nothing is redundant, though the second clause packs two distinct ideas (required file types and reader serving) together.

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

Completeness3/5

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

The output schema covers the returned URL, so the description needn't explain returns. What remains missing is the destructive/overwrite behavior implied by the annotations and the 'site' parameter, which is the main risk an agent must understand before calling a write tool that replaces a site.

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 coverage is 100%, so both parameters are already documented, and the description adds the folder-content contract (index.html or .md/.pdf) that constrains 'path'. It adds no semantics for 'site' (e.g., whether publishing over an existing id replaces content), so the baseline 3 is appropriate.

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?

States a specific verb and resource ('Publishes a folder of static files') and adds the outcome ('returns its URL'), which is precise enough to act on. It never distinguishes itself from the sibling publish_files, so an agent must infer the folder-vs-files split from the names alone.

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?

No when-to-use guidance, no mention of the sibling publish_files as the alternative, and no prerequisites (auth, ownership of the target site). The only routing signal is the tool name itself; the description offers none.

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