Skip to main content
Glama

AfterLaunch

by io.afterlaunch
OverviewDiscussionsAdmin

ship_move

Record completion only after the founder explicitly confirms it. Use prepared_result after reviewing the current prepared attempt, or independent_work when the founder completed it separately. Site changes need a live published_url to ship; without one they stay prepared. This records an attestation; it never publishes anything. Free; requires the 'act' scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNo
job_idYes
move_idYesMove id (uuid), from list_feed.
attempt_idYes
final_textNoOptional. Only the words the founder actually posted, exactly as they went out; never your rewrite or the draft. Used only to learn how they write, for a post or reply they published; it marks nothing published. Omit it if unknown.
planned_urlNoFuture address of a prepared page on the founder's own site.
published_urlNoThe actual public URL, when the completed task has one. This is distinct from a prepared asset.
completion_kindYes
founder_confirmedYes
expected_move_stateNoRequired with expected_move_updated_at for independent_work.
expected_legacy_stateNoget_move: prepared_result.legacy_state ?? state.
expected_move_updated_atNoRequired with expected_move_state for independent_work.
expected_legacy_updated_atNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / final_text
      Added value: +{
+  "description": "Optional. Only the words the founder actually posted, exactly as they went out; never your rewrite or the draft. Used only to learn how they write, for a post or reply they published; it marks nothing published. Omit it if unknown.",
+  "maxLength": 20000,
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / planned_url
      Added value: +{
+  "description": "Future address of a prepared page on the founder's own site.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / expected_legacy_state / description
      Added value: +"get_move: prepared_result.legacy_state ?? state."
  4. Changed12 schema fields changed
    • removedInput schema / properties / asset_url
      Removed value: -{
-  "description": "Optional confirmed live URL of the shipped asset.",
-  "type": "string"
-}
    • addedInput schema / properties / attempt_id
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / completion_kind
      Added value: +{
+  "enum": [
+    "prepared_result",
+    "independent_work"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / expected_legacy_state
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / expected_legacy_updated_at
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / expected_move_state
      Added value: +{
+  "description": "Required with expected_move_updated_at for independent_work.",
+  "enum": [
+    "pending",
+    "taken_on",
+    "shipped",
+    "skipped",
+    "archived",
+    "expired",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / expected_move_updated_at
      Added value: +{
+  "description": "Required with expected_move_state for independent_work.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / founder_confirmed
      Added value: +{
+  "const": true,
+  "type": "boolean"
+}
    • addedInput schema / properties / job_id
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / note
      Added value: +{
+  "maxLength": 2000,
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedInput schema / properties / published_url
      Added value: +{
+  "description": "The actual public URL, when the completed task has one. This is distinct from a prepared asset.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • changedInput schema / required
      Previous value: -[
-  "move_id"
-]New value: +[
+  "move_id",
+  "completion_kind",
+  "job_id",
+  "attempt_id",
+  "founder_confirmed"
+]
  5. Changed2 schema fields changed
    • changedInput schema / properties / asset_url / description
      Previous value: -"Optional confirmed live URL of the shipped marketing asset."New value: +"Optional confirmed live URL of the shipped asset."
    • changedInput schema / properties / move_id / description
      Previous value: -"The growth move id (uuid), from list_feed."New value: +"Move id (uuid), from list_feed."
  6. First observed

TDQS

A4.1/5.0
Behavior5/5

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

With only readOnlyHint=false and destructiveHint=false in annotations, the description carries real added burden and meets it: it discloses the act scope requirement, that the call is free, and most importantly that it 'records an attestation; it never publishes anything' – a non-obvious side-effect profile for a tool named 'ship'.

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?

Four dense sentences, front-loaded with the confirmation gate, then the kind selection, then the published_url rule, then the attestation/scope footer. No sentence is filler.

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 13-param, no-output-schema tool this covers the decision logic and safety profile well, and the attestation framing tells the agent what the call effectively returns (nothing published). The gap is the undocumented expected_* concurrency parameters and their required-with relationships.

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 only 54% across 13 params. The description adds genuine meaning for completion_kind, published_url (explicitly distinguished from planned_url), and final_text, but says nothing about the optimistic-concurrency params (expected_move_state/expected_move_updated_at, required for independent_work per the schema) or how job_id/attempt_id relate.

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 (record) and object (completion of a move), and the gating condition (founder confirmation). It is distinguishable from lifecycle siblings like accept_move, review_move, skip_move, and undo_move, though it never names them explicitly.

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 concrete selection guidance between the two completion_kind values ('prepared_result after reviewing the current prepared attempt' vs 'independent_work when the founder completed it separately') plus a conditional rule (site changes need a live published_url or they stay prepared). It does not, however, contrast against the other move-lifecycle siblings.

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

All AfterLaunch 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