Skip to main content
Glama

smart_bundle

Merge 2–8 related symbols across files into one bundle with per-file skeletons, deduplicated imports, and dependency signatures, replacing multiple reads in one roundtrip.

Instructions

Reads 2-8 related symbols across files as ONE merged bundle: per-file skeletons, deduplicated shared imports, merged 1-hop dep signatures. Replaces 3+ separate smart_read_file calls in a single roundtrip.

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": {
      "targets": "<targets>"
    },
    "name": "smart_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetsYesUp to 8 {path, symbol} targets; several symbols of one file = separate entries
dep_modeNoParity only; bundles always merge signatures
force_fullNoBypass session pointer dedup
include_depsNoInclude merged 1-hop dep signatures (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv3.1.5
    • changedInput schema / properties / dep_mode / description
      Previous value: -"Optional: kept for parity with smart_read_file; signatures are always merged for bundles"New value: +"Parity only; bundles always merge signatures"
    • changedInput schema / properties / force_full / description
      Previous value: -"Optional: bypass session pointer deduplication"New value: +"Bypass session pointer dedup"
    • changedInput schema / properties / include_deps / description
      Previous value: -"Optional: include merged 1-hop dependency signatures (default: true)"New value: +"Include merged 1-hop dep signatures (default true)"
    • changedInput schema / properties / targets / description
      Previous value: -"Up to 8 {path, symbol} targets; list several symbols of the same file as separate entries"New value: +"Up to 8 {path, symbol} targets; several symbols of one file = separate entries"
    • changedInput schema / properties / targets / items / properties / path / description
      Previous value: -"File path to code file (relative to workspace or absolute)"New value: +"File path (relative or absolute)"
    • changedInput schema / properties / targets / items / properties / symbol / description
      Previous value: -"Optional symbol to keep unfolded (class, function, or component name)"New value: +"Optional symbol to keep unfolded"
  2. First observedv2.8.4

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does usefully disclose merge/dedup behavior and hints at session-level pointer dedup via force_full, but says nothing about read-only safety, what happens with unresolvable paths/symbols, or how the bundle is ordered. Solid but not a complete behavioral contract for a tool with zero annotation coverage.

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?

Two dense sentences with zero filler: capability and payload first, differentiation/selection rule second. Every clause carries information an agent needs.

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 4-parameter, no-annotation, no-output-schema tool, the description adequately conveys what a call produces and why the batching exists. Gaps remain around failure modes (unknown symbol, unreadable path) and output ordering, which matter for a tool that merges heterogeneous reads.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so a 3 is the floor; the description earns more by tying 'merged 1-hop dep signatures' to include_deps and 'session pointer dedup' to force_full, giving those flags operational meaning beyond their schema strings. It stays silent on why dep_mode exists and on the 8-target cap beyond the schema's maxItems.

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 (reads 2-8 related symbols as one merged bundle) and enumerates exactly what the bundle contains: per-file skeletons, deduplicated shared imports, merged 1-hop dep signatures. It also distinguishes itself from the sibling smart_read_file by declaring itself a replacement for 3+ of those calls.

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 selection rule: use this instead of 3+ separate smart_read_file calls in a single roundtrip, naming the alternative explicitly. It does not state the converse (for a single file/symbol, use smart_read_file instead), so the threshold is implied rather than fully spelled out.

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