Skip to main content
Glama

DropTheHassle

by io.github.bosmdavid-gif
OverviewDiscussionsAdmin

Deploy site

deploy_site
Destructive

Uploads site files and returns a live HTTPS link (name.dropthehassle.app) and a claim link (claim_url). Works without an account. Files are sent inline as path, content and encoding (utf8 or base64). This server cannot read a folder on the caller's computer. The published files are index.html at the top, or the built folder dist/, build/, out/, _site/, .output/public or docs/. With an account, site names the site to update and name is omitted; without site the oldest reserved address on the account is filled. Does not buy a name. Size limits: 25 MB and 1,000 files before the site is claimed, 100 MB and 5,000 files when signed in.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoAddress label, for example "lisas-bakery" for lisas-bakery.dropthehassle.app. Used when creating a site. Works with no account token.
siteNoOptional site address to update, for example myproject.dropthehassle.app. Absent fills the oldest reserved address on the account.
slugNoSame as name. Older clients send this.
emailNoOptional. Where the claim link and up to 3 reminders are sent. Ask after go-live, not before. Do not make one up. Omit it to publish with a claim link only.
filesYesSite files sent inline. Each item has path, content, and encoding utf8 or base64. node_modules, .git and hidden files are not part of the site. .well-known is allowed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / email / description
      Previous value: -"The email address the claim link is sent to. Used for that link and up to 3 reminders about this site. Required when no account is connected."New value: +"Optional. Where the claim link and up to 3 reminders are sent. Ask after go-live, not before. Do not make one up. Omit it to publish with a claim link only."
  2. Changed4 schema fields changed
    • changedInput schema / properties / email / description
      Previous value: -"The user's own email address, as they typed it to you in this conversation. Used only for the claim link and up to 3 reminders about this site. Required when no account token is set. If you don't have it, ask the user for their email first. Never invent, guess or reuse one."New value: +"The email address the claim link is sent to. Used for that link and up to 3 reminders about this site. Required when no account is connected."
    • changedInput schema / properties / files / description
      Previous value: -"Site files sent inline. Each item has path, content, and encoding utf8 or base64. Leave out node_modules, .git and hidden files. .well-known is allowed."New value: +"Site files sent inline. Each item has path, content, and encoding utf8 or base64. node_modules, .git and hidden files are not part of the site. .well-known is allowed."
    • changedInput schema / properties / name / description
      Previous value: -"The free address label, for example \"lisas-bakery\" for lisas-bakery.dropthehassle.app. Pass the name the human confirmed. If they have no preference, pass your proposal. Works with no account token."New value: +"Address label, for example \"lisas-bakery\" for lisas-bakery.dropthehassle.app. Used when creating a site. Works with no account token."
    • changedInput schema / properties / site / description
      Previous value: -"Optional: the address of an existing site to update, e.g. myproject.dropthehassle.app (from list_sites). Omit it to fill the oldest reserved site on this account."New value: +"Optional site address to update, for example myproject.dropthehassle.app. Absent fills the oldest reserved address on the account."
  3. Changed2 schema fields changed
    • addedInput schema / properties / name
      Added value: +{
+  "description": "The free address label, for example \"lisas-bakery\" for lisas-bakery.dropthehassle.app. Pass the name the human confirmed. If they have no preference, pass your proposal. Works with no account token.",
+  "type": "string"
+}
    • changedInput schema / properties / slug / description
      Previous value: -"Optional: the address label for a NEW site, e.g. \"myproject\". Errors when taken, so propose another."New value: +"Same as name. Older clients send this."
  4. Changed1 schema field changed
    • addedInput schema / properties / email
      Added value: +{
+  "description": "The user's own email address, as they typed it to you in this conversation. Used only for the claim link and up to 3 reminders about this site. Required when no account token is set. If you don't have it, ask the user for their email first. Never invent, guess or reuse one.",
+  "type": "string"
+}
  5. Changed2 schema fields changed
    • addedInput schema / properties / site
      Added value: +{
+  "description": "Optional: the address of an existing site to update, e.g. myproject.dropthehassle.app (from list_sites). Omit it to fill the oldest reserved site on this account.",
+  "type": "string"
+}
    • removedInput schema / properties / site_id
      Removed value: -{
-  "description": "Optional: an existing site to update. Omit it to fill the oldest reserved site on this account.",
-  "type": "number"
-}
  6. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial context beyond the annotations (destructiveHint/openWorldHint): anonymous operation, returned links, the fact that the server cannot read the caller's filesystem, and concrete size limits (25 MB / 1,000 files unclaimed vs 100 MB / 5,000 signed in). These are exactly the operational facts an agent needs before invoking a destructive write.

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?

Front-loads the core action and return values, then layers in constraints with no filler sentences. It is a dense single paragraph, so a bulleted grouping of limits/conventions would read slightly better, but every sentence earns its place.

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 a destructive, account-optional publishing tool with no output schema, the description covers returns (live link, claim_url), auth modes, file conventions and quotas. Nothing material is left for the agent to infer before calling.

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, but the description adds genuine meaning: the name-vs-site interaction (with an account, site targets an existing site and name is omitted; without site the oldest reserved address is filled), how slug relates to name, and email's purpose. This clarifies behavior the schema describes only per-field.

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?

States a specific verb and resource ("Uploads site files") plus the return artifacts (live HTTPS link, claim link), which cleanly separates it from siblings like edit_site_file, rollback_site and claim_site. An agent can tell what this does without opening the schema.

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?

Provides strong context on when it applies: works without an account, cannot read a local folder, and which entry files are published (index.html or dist/, build/, out/, _site/, .output/public, docs/). It also flags an exclusion ("Does not buy a name"), but never names an explicit alternative sibling for edge cases, so it falls just short of 5.

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

All DropTheHassle 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