Skip to main content
Glama

task_pack

Read-onlyIdempotent

Assembles the minimum useful working set for a coding task by ranking relevant files and including nearby tests, recent diffs, project memory, and risks.

Instructions

Assemble the minimum useful working set for a task: ranked files, nearby tests, recent diffs, memory, and risks.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "task_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoAbsolute project root. Omit only where this session started; required elsewhere and on every subagent call.
taskYesTask description or engineering objective.
formatNoReturn plain text or structured JSON. Default: text.
presetNobalanced (default) or keyword_only for zero-provider lexical discovery.
max_filesNoMaximum ranked files to include. Default: 8.
graph_hopsNoRelated import context: 0, 1 or 2 hops. Default 1 with CONTEXTPRO_CONNECTED_CONTEXT=true, otherwise 0. Relationships are heuristic.
max_memoryNoMaximum memory hits to include. Default: 3, max: 10.
max_tokensNoFinal response budget estimated as UTF-8 bytes/4, not tokenizer tokens. Default: 3000.
include_testsNoInclude nearby tests. Default: true.
include_memoryNoInclude project memory hits. Default: true.
graph_max_filesNoMaximum additional graph-related file pointers. Default: 4.
previous_context_idNoContext ID from a previous packet you still hold; return a delta. Omit after context loss to recover full context.
include_recent_diffsNoInclude recent file-level diffs. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.0
    • changedInput schema / properties / root / description
      Previous value: -"Absolute project root. Required with linked worktrees; subagents must pass their own worktree root on every call."New value: +"Absolute project root. Omit only where this session started; required elsewhere and on every subagent call."
  2. First observedv1.4.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is fully covered structurally. The description adds value by disclosing the packet composition (files, tests, diffs, memory, risks), which stands in for the absent output schema. It says nothing about cost, provider dependency, or delta semantics from previous_context_id.

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?

A single front-loaded sentence with no filler; the resource and its contents come first and every clause adds information. Nothing is redundant with the schema or the title.

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-parameter aggregator with no output schema, the description names the return contents, which is the most important missing piece. Remaining gaps are usage routing (this vs. search/grep) and the root/delta calling conventions, both of which the schema documents on its own.

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 100%, and every parameter carries a substantive inline description including defaults, ranges, and the token-estimation caveat, so the schema does the heavy lifting. The description contributes no additional parameter meaning, which is the expected baseline here.

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?

Uses a specific verb ("assemble") plus a defined artifact ("minimum useful working set for a task") and enumerates its contents: ranked files, nearby tests, recent diffs, memory, risks. An agent can picture the output. It stops short of naming sibling tools it supersedes (search, grep, exact_references, skeleton), so differentiation relies on inference.

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

Usage Guidelines3/5

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

The phrase "for a task" implies context-gathering at task start, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many retrieval siblings. An agent must guess whether to call task_pack or fall back to search/grep.

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