Skip to main content
Glama

AfterLaunch

by io.afterlaunch
OverviewDiscussionsAdmin

Pick up a job

pick_up_job
Destructive

Try to claim one queued preparation attempt. Pass job_id and the exact nullable attempt_id of a queued job. Start work only when the response says claim_won:true. An unchanged result is a non-winner and must not start work. Free; requires the 'act' scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
job_idYesJob id (uuid), from list_queue.
attempt_idYesExact attempt id from list_queue; null only for a stored legacy job.
session_urlNoOptional. The launch already gave your user the link to this session; pass it only when you opened this session yourself and can see its address.
site_repositoryNoOptional, for a routine working a site move: the repository it can write to, as owner/name, or null if it has none. Omit it to say nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / site_repository
      Added value: +{
+  "description": "Optional, for a routine working a site move: the repository it can write to, as owner/name, or null if it has none. Omit it to say nothing.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / session_url / description
      Previous value: -"Your own session URL, if you have one, so the founder can open where the work is happening."New value: +"Optional. The launch already gave your user the link to this session; pass it only when you opened this session yourself and can see its address."
  3. Changed2 schema fields changed
    • addedInput schema / properties / attempt_id
      Added value: +{
+  "description": "Exact attempt id from list_queue; null only for a stored legacy job.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • changedInput schema / required
      Previous value: -[
-  "job_id"
-]New value: +[
+  "job_id",
+  "attempt_id"
+]
  4. Changed1 schema field changed
    • addedInput schema / properties / session_url
      Added value: +{
+  "description": "Your own session URL, if you have one, so the founder can open where the work is happening.",
+  "type": "string"
+}
  5. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only flag it as a non-read-only, destructive, closed-world operation. The description goes further: it discloses the authorization requirement ('act' scope), the cost ('Free'), and crucially the claim semantics and response contract (claim_won:true, non-winner on unchanged result) that govern whether downstream work may start. It doesn't explain failure/conflict handling or concurrency edge cases, keeping it short of a 5.

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?

Five short sentences, front-loaded with the action and its argument source, then the proceed/no-proceed rule, then cost and auth. Every sentence carries a distinct operational fact with no 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?

With no output schema, the description carries the response burden and does partially: it names claim_won:true as the success signal and defines the non-winner case. However, it doesn't describe other possible response fields or error/conflict outcomes for a claim-style operation, leaving a small gap for an agent deciding how to react to a failed pickup.

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 description coverage is 100%, so both required params and both optionals are already documented in the schema. The description reinforces the exactness of attempt_id ('the exact nullable attempt_id') and its null-only-for-legacy nuance, but adds no syntax or format detail beyond what the schema provides. 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 and resource — 'Try to claim one queued preparation attempt' — and pins it to a concrete workflow by naming list_queue as the source of job_id/attempt_id. An agent can distinguish this from sibling list_queue (read-only listing) and report_job without opening either 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 clear operating condition: only start work when the response says claim_won:true, and an unchanged result must not start work. It also routes the agent to list_queue for the required ids. It stops short of naming explicit alternatives or a when-not-to-use case, so it's strong context rather than a full decision matrix.

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
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