Skip to main content
Glama

bear_context_ingest

Read-onlyIdempotent

Lists untriaged files from the inbox directory with filename, size, content preview, and YAML front matter for review before taking action.

Instructions

Scan the inbox/ directory and list all untriaged files. Returns filename, size, content preview (first 500 chars), and any detected YAML front matter for each file. Does NOT modify anything — use bear_context_triage to act on files.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The tool definition and handler for 'bear_context_ingest'. The buildArgs function constructs the CLI args ['context', 'ingest', '--json'] which are executed via execBcliWithReauth in index.ts. The tool has no input parameters and is marked as read-only/idempotent.
    bear_context_ingest: {
      tool: {
        name: "bear_context_ingest",
        description:
          "Scan the inbox/ directory and list all untriaged files. Returns filename, size, content preview (first 500 chars), and any detected YAML front matter for each file. Does NOT modify anything — use bear_context_triage to act on files.",
        inputSchema: {
          type: "object" as const,
          properties: {},
        },
        annotations: {
          readOnlyHint: true,
          destructiveHint: false,
          idempotentHint: true,
        },
      },
      buildArgs: () => ["context", "ingest", "--json"],
    },
  • Tools are registered with the MCP server by mapping all tool definitions from tools.ts via ListToolsRequestSchema handler.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: Object.values(tools).map((t) => t.tool),
    }));
  • The input schema for bear_context_ingest — an empty object with no properties, since this tool takes no arguments.
    inputSchema: {
      type: "object" as const,
      properties: {},
    },
    annotations: {
Behavior4/5

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint. Description adds non-contradictory details about return content (first 500 chars, YAML front matter) but no extra safety context.

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 sentences, no extraneous words. First sentence states action and results, second clarifies non-destructive nature and alternative tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple with no params or output schema; description covers all needed context: what it does, returns, and relevant sibling for actions.

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?

No parameters exist; description explains tool operation clearly. Baseline 4 as zero params. Schema coverage 100%.

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?

Description clearly states verb 'scan' and resource 'inbox/ directory' for untriaged files, lists return fields, and distinguishes from sibling 'bear_context_triage'.

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 says to use for listing untriaged files and directs to 'bear_context_triage' for acting on files, with a clear 'does NOT modify anything'.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mreider/better-bear'

If you have feedback or need assistance with the MCP directory API, please join our Discord server