Skip to main content
Glama
Sign In
Solumbe

Solumbe

by BASHBOP
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Context Pack

context_pack
Read-only

Generates a task-aware local context packet containing primary files, related files, tests, and validation commands so coding agents can start from the right repository context.

Instructions

Generate a task-aware local context packet with primary files, related files, tests, and validation commands. Deterministic by default; online:true also asks a read model for the request's intent and which candidate files it needs, reported under modelRead.

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": {
      "query": "<query>"
    },
    "name": "context_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoRepository path. Defaults to current working directory.
limitNoMaximum primary, related, and test files per section. Defaults to 8.
pathsNoRepository paths for a multi-repo context packet. Omitted, `path` plus the `companions` listed in its .solumberc.json.
queryYesTask or question to gather context for.
onlineNoAsk a read model (TypeSafe's Jev or Claude) for the request's intent and each candidate file's relevance, applying confident answers. Needs TYPESAFE_API_KEY or ANTHROPIC_API_KEY; without either the pack is unchanged. Defaults to false.
includeEvidenceNoInclude per-file imports, exports, and symbol slices as source evidence. Defaults to false to keep the packet compact.
includeMarkdownNoReturn a compact human-readable markdown report instead of the full JSON packet. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.10.0
    • changedInput schema / properties / online / description
      Previous value: -"Ask a read model (TypeSafe's Jev, or Claude through forced tool use) to read the request (intent, and relevance of each candidate file) in one call, and apply answers that clear their confidence gate. Needs TYPESAFE_API_KEY or ANTHROPIC_API_KEY (SOLUMBE_READ_PROVIDER picks one when both are set); without either the pack is returned unchanged with modelRead.source offline. Defaults to false."New value: +"Ask a read model (TypeSafe's Jev or Claude) for the request's intent and each candidate file's relevance, applying confident answers. Needs TYPESAFE_API_KEY or ANTHROPIC_API_KEY; without either the pack is unchanged. Defaults to false."
  2. Changed1 schema field changedv4.7.2
    • changedInput schema / properties / online / description
      Previous value: -"Ask TypeSafe's Jev to read the request (intent, and relevance of each candidate file) in one call, and apply answers that clear their confidence gate. Needs TYPESAFE_API_KEY; without one the pack is returned unchanged with modelRead.source offline. Defaults to false."New value: +"Ask a read model (TypeSafe's Jev, or Claude through forced tool use) to read the request (intent, and relevance of each candidate file) in one call, and apply answers that clear their confidence gate. Needs TYPESAFE_API_KEY or ANTHROPIC_API_KEY (SOLUMBE_READ_PROVIDER picks one when both are set); without either the pack is returned unchanged with modelRead.source offline. Defaults to false."
  3. Changed1 schema field changedv3.5.1
    • changedInput schema / properties / paths / description
      Previous value: -"Repository paths for a multi-repo context packet. Omitted, `path` plus the `companions` listed in its .otitorc.json."New value: +"Repository paths for a multi-repo context packet. Omitted, `path` plus the `companions` listed in its .solumberc.json."
  4. Changed1 schema field changedv3.5.0
    • changedInput schema / properties / paths / description
      Previous value: -"Repository paths for a multi-repo context packet."New value: +"Repository paths for a multi-repo context packet. Omitted, `path` plus the `companions` listed in its .otitorc.json."
  5. Changed1 schema field changedv1.14.1
    • addedInput schema / properties / online
      Added value: +{
+  "description": "Ask TypeSafe's Jev to read the request (intent, and relevance of each candidate file) in one call, and apply answers that clear their confidence gate. Needs TYPESAFE_API_KEY; without one the pack is returned unchanged with modelRead.source offline. Defaults to false.",
+  "type": "boolean"
+}
  6. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Beyond readOnlyHint/openWorldHint, it discloses that default behavior is deterministic and that online:true reaches an external read model, gracefully degrading ("without either the pack is unchanged") when no key is set. It also explains that includeEvidence defaults off to keep the packet compact. Costs such as runtime or file-count tradeoffs are not mentioned, 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?

Two tightly packed sentences: the first defines the artifact, the second defines the only behavioral branch (online). No filler, no repetition of the schema, and the core output is front-loaded.

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 and seven parameters, the description does the necessary work: it names the packet's sections, the deterministic default, and the online augmentation path. What remains thin is the shape of the returned packet and multi-repo behavior, both of which live entirely in the schema descriptions.

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 the baseline is 3, but the description adds outcome semantics the schema lacks: online results surface under modelRead and only confident answers are applied, and includeMarkdown switches the return shape to a markdown report. That goes beyond merely restating parameter names.

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 and resource ("Generate a task-aware local context packet") and enumerates the packet's contents: primary files, related files, tests, validation commands. That is far more informative than the title, but it never names a sibling, so an agent must infer on its own that this differs from repo_search, repo_map, or review_context.

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 description signals the main usage fork (deterministic by default vs. online:true consulting a read model) and the API-key prerequisite. It never says when this tool should be chosen over repo_search or review_context, or when a local packet is the wrong choice, so routing context is only implied.

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