Skip to main content
Glama
ihorponom

agentpack

by ihorponom
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

task_start

Start a coherent work phase by creating a Task Passport under .agentpack/. Refuses if a task is active; declare writeScope to protect boundaries.

Instructions

Create a new Task Passport and make it current, persisting it under .agentpack/. Call when starting a coherent phase of work and no task is active; it refuses to replace an active, blocked, or verifying current task — park or finalize that task first. Declare writeScope so the task gate can protect the task's boundaries.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
riskNoRisk level of the task.
tagsNoFree-form labels for grouping tasks.
titleYesShort imperative task title.
objectiveNoWhat done looks like for this task.
writeScopeNoRepo-relative prefix paths this task is allowed to modify. A directory path includes its children; globs are not supported.
constraintsNoRules the work must respect.
nextActionsNoInitial concrete next steps.
repositoriesNoAdditional checkouts keyed by id; the ledger root is primary. Local updates append scopes; imported bindings use only the supplied local scope. Requires an active task with pending or unknown verification.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.11.0
    • addedInput schema / properties / repositories
      Added value: +{
+  "description": "Additional checkouts keyed by id; the ledger root is primary. Local updates append scopes; imported bindings use only the supplied local scope. Requires an active task with pending or unknown verification.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "description": "Stable unique repository id; primary is reserved.",
+        "type": "string"
+      },
+      "worktree": {
+        "description": "Local Git checkout root, absolute or relative to the pack root.",
+        "type": "string"
+      },
+      "writeScope": {
+        "description": "Non-empty repository-relative prefix paths; dot means the whole checkout.",
+        "items": {
+          "type": "string"
+        },
+        "minItems": 1,
+        "type": "array"
+      }
+    },
+    "required": [
+      "id",
+      "worktree",
+      "writeScope"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
  2. Changed7 schema fields changedv1.4.0
    • addedInput schema / properties / constraints / description
      Added value: +"Rules the work must respect."
    • addedInput schema / properties / nextActions / description
      Added value: +"Initial concrete next steps."
    • addedInput schema / properties / objective / description
      Added value: +"What done looks like for this task."
    • addedInput schema / properties / risk / description
      Added value: +"Risk level of the task."
    • addedInput schema / properties / tags / description
      Added value: +"Free-form labels for grouping tasks."
    • addedInput schema / properties / title / description
      Added value: +"Short imperative task title."
    • addedInput schema / properties / writeScope / description
      Added value: +"Repo-relative prefix paths this task is allowed to modify. A directory path includes its children; globs are not supported."
  3. First observedv1.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already give the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds state preconditions not visible in annotations: it refuses to replace an active/blocked/verifying task and persists to .agentpack/. It does not describe the created artifact's shape or failure mode details, so it stops 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and persistence target before the gating rules. Dense but every clause carries distinct information; no filler or restatement of the name.

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-parameter creation tool with no output schema, the description covers purpose, exclusivity rules, state preconditions, and the most safety-relevant parameter. It omits any indication of what the tool returns (e.g., the new task id), which an agent creating a task might reasonably need.

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 the schema already documents all 8 parameters, establishing a baseline of 3. The description adds rationale for writeScope ('so the task gate can protect the task's boundaries') but leaves the other seven parameters, including the multi-repo 'repositories' binding, entirely to the schema.

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 concrete verb and resource (create a Task Passport) plus the side effect (makes it current, persists under .agentpack/). This clearly separates it from task_switch, task_update, and task_finalize in the sibling list, since those operate on an existing task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the invocation condition ('starting a coherent phase of work and no task is active') and the exclusion ('refuses to replace an active, blocked, or verifying current task'), then names the alternative actions ('park or finalize that task first'). Nothing about when to reach for this tool is left to inference.

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

Deploy Server

Other Tools