Skip to main content
Glama
Sign In

Hatch

by com.viberooster
OverviewDiscussionsAdmin

Upload files to an existing site

upload
DestructiveIdempotent

Add or replace files on an EXISTING roost. Pass hatchId plus a manifest listing each file's path, size, and optional content type. Returns one presigned PUT URL per file — upload bytes directly via HTTP (e.g. curl -T file.png -H 'Content-Type: image/png' "$url"). Files go live immediately as each PUT completes; no separate publish call is needed. Use after regenerating a dashboard locally; Hatch does not schedule regenerations.

Input Schema

NameRequiredDescriptionDefault
policyNoHITL policy override. `optional` does not open a review (call `await_decision`). Under `required`, may fork a sibling `{slug}-vN` instead of overwriting. `good_effort` still auto-opens and supersedes.
hatchIdNoHatch id from the original hatch response.
manifestYes
tenantIdNoLegacy alias for `hatchId` from the original hatch response.
hitlTitleNoModal title for auto-opened HITL.
webhookUrlNoWebhook for auto-opened HITL.
sessionTokenNoOptional paired session token from poll_pairing (when Authorization headers are unavailable).
expiresSecondsNoURL TTL in seconds (default 3600).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / policy / description
      Previous value: -"HITL policy override. Under `required`, may fork a sibling `{slug}-vN` instead of overwriting."New value: +"HITL policy override. `optional` does not open a review (call `await_decision`). Under `required`, may fork a sibling `{slug}-vN` instead of overwriting. `good_effort` still auto-opens and supersedes."
    • changedInput schema / properties / policy / enum
      Previous value: -[
-  "required",
-  "good_effort"
-]New value: +[
+  "required",
+  "good_effort",
+  "optional"
+]
  2. Changed3 schema fields changed
    • addedInput schema / properties / hitlTitle
      Added value: +{
+  "description": "Modal title for auto-opened HITL.",
+  "type": "string"
+}
    • addedInput schema / properties / policy
      Added value: +{
+  "description": "HITL policy override. Under `required`, may fork a sibling `{slug}-vN` instead of overwriting.",
+  "enum": [
+    "required",
+    "good_effort"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / webhookUrl
      Added value: +{
+  "description": "Webhook for auto-opened HITL.",
+  "type": "string"
+}
  3. Changed3 schema fields changed
    • addedInput schema / properties / hatchId
      Added value: +{
+  "description": "Hatch id from the original hatch response.",
+  "type": "string"
+}
    • changedInput schema / properties / tenantId / description
      Previous value: -"Tenant id from the original hatch response."New value: +"Legacy alias for `hatchId` from the original hatch response."
    • changedInput schema / required
      Previous value: -[
-  "tenantId",
-  "manifest"
-]New value: +[
+  "manifest"
+]
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (destructive/idempotent/openWorld), the description discloses the two-step mechanism: it returns one presigned PUT URL per file and bytes are uploaded directly via HTTP, with files going live as each PUT completes. This is high-value behavioral context the annotations cannot convey. It does not cover auth/permission requirements, which is the main remaining gap.

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?

Front-loaded with the core action and the EXISTING constraint, followed by the input, the return mechanism, and the workflow context. Every sentence adds distinct information with zero padding.

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 an 8-param, nested-schema tool with no output schema, the description compensates by explaining the return (presigned URLs) and the follow-up HTTP PUT step. The policy/HITL/session/expiry params are left to the schema, which is reasonable but not fully addressed.

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 88%, so the schema already documents hatchId, manifest structure, policy, and the HITL/webhook params. The description restates the manifest fields (path, size, content type) rather than adding semantic detail, so baseline 3 is appropriate.

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 (add/replace files) and resource (an EXISTING roost), and the capitalised 'EXISTING' cleanly separates it from the creation-oriented `hatch` sibling. An agent can tell what this does and where it applies 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?

Gives a concrete trigger ('Use after regenerating a dashboard locally; Hatch does not schedule regenerations') and clarifies no separate publish call is needed, which heads off a common wrong workflow. It does not name explicit alternatives or exclusions, so it stops short of full when/when-not guidance.

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

All Hatch toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources