Skip to main content
Glama

bear_context_triage

Idempotent

Triage inbox files by moving to external folder, creating a Bear note with context tag, or deleting. Automatically regenerates the index.

Instructions

Triage a file in the inbox. Three actions: 'keep' moves it to external/ with optional group/summary metadata. 'push_to_bear' creates a Bear note tagged #context (+ optional subtag) and deletes the inbox file. 'discard' deletes the file. All actions regenerate the index.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filenameYesFilename in inbox/ to triage
actionYesTriage action: keep (move to external/), push_to_bear (create Bear note), or discard (delete)
groupNoGroup label (used with 'keep' action)
subtagNoSub-tag for Bear note (used with 'push_to_bear' action, e.g., 'jira' → #context/jira)
summaryNoShort summary (used with 'keep' action)

Implementation Reference

  • Tool definition and input schema for bear_context_triage. Accepts filename (required), action (required, enum: keep/push_to_bear/discard), group, subtag, and summary.
    bear_context_triage: {
      tool: {
        name: "bear_context_triage",
        description:
          "Triage a file in the inbox. Three actions: 'keep' moves it to external/ with optional group/summary metadata. 'push_to_bear' creates a Bear note tagged #context (+ optional subtag) and deletes the inbox file. 'discard' deletes the file. All actions regenerate the index.",
        inputSchema: {
          type: "object" as const,
          properties: {
            filename: {
              type: "string",
              description: "Filename in inbox/ to triage",
            },
            action: {
              type: "string",
              enum: ["keep", "push_to_bear", "discard"],
              description:
                "Triage action: keep (move to external/), push_to_bear (create Bear note), or discard (delete)",
            },
            group: {
              type: "string",
              description:
                "Group label (used with 'keep' action)",
            },
            subtag: {
              type: "string",
              description:
                "Sub-tag for Bear note (used with 'push_to_bear' action, e.g., 'jira' → #context/jira)",
            },
            summary: {
              type: "string",
              description:
                "Short summary (used with 'keep' action)",
            },
          },
          required: ["filename", "action"],
        },
        annotations: {
          readOnlyHint: false,
          destructiveHint: false,
          idempotentHint: true,
        },
      },
  • buildArgs function that constructs the command-line arguments to invoke 'bcli context triage' with the filename, action, --json flag, and optional --group, --subtag, --summary flags.
      buildArgs: (input) => {
        const args = [
          "context",
          "triage",
          String(input.filename),
          String(input.action),
          "--json",
        ];
        if (input.group) args.push("--group", String(input.group));
        if (input.subtag) args.push("--subtag", String(input.subtag));
        if (input.summary) args.push("--summary", String(input.summary));
        return args;
      },
    },
  • Registration of bear_context_triage in the tools record, mapping the tool definition and buildArgs to the 'bear_context_triage' key.
    bear_context_triage: {
      tool: {
        name: "bear_context_triage",
        description:
          "Triage a file in the inbox. Three actions: 'keep' moves it to external/ with optional group/summary metadata. 'push_to_bear' creates a Bear note tagged #context (+ optional subtag) and deletes the inbox file. 'discard' deletes the file. All actions regenerate the index.",
        inputSchema: {
          type: "object" as const,
          properties: {
            filename: {
              type: "string",
              description: "Filename in inbox/ to triage",
            },
            action: {
              type: "string",
              enum: ["keep", "push_to_bear", "discard"],
              description:
                "Triage action: keep (move to external/), push_to_bear (create Bear note), or discard (delete)",
            },
            group: {
              type: "string",
              description:
                "Group label (used with 'keep' action)",
            },
            subtag: {
              type: "string",
              description:
                "Sub-tag for Bear note (used with 'push_to_bear' action, e.g., 'jira' → #context/jira)",
            },
            summary: {
              type: "string",
              description:
                "Short summary (used with 'keep' action)",
            },
          },
          required: ["filename", "action"],
        },
        annotations: {
          readOnlyHint: false,
          destructiveHint: false,
          idempotentHint: true,
        },
      },
      buildArgs: (input) => {
        const args = [
          "context",
          "triage",
          String(input.filename),
          String(input.action),
          "--json",
        ];
        if (input.group) args.push("--group", String(input.group));
        if (input.subtag) args.push("--subtag", String(input.subtag));
        if (input.summary) args.push("--summary", String(input.summary));
        return args;
      },
    },
  • CallToolRequestSchema handler that looks up the tool by name, calls handler.buildArgs(params), and executes via execBcliWithReauth or execBcliWithStdinAndReauth.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: input } = request.params;
      const handler = tools[name];
    
      if (!handler) {
        return {
          content: [{ type: "text", text: `Unknown tool: ${name}` }],
          isError: true,
        };
      }
    
      const params = (input ?? {}) as Record<string, unknown>;
    
      // Validate bear_edit_note: need at least one edit operation
      if (name === "bear_edit_note") {
        const hasAppend = params.append_text !== undefined;
        const hasBody = params.body !== undefined;
        const hasSetFm = params.set_frontmatter !== undefined &&
          Object.keys(params.set_frontmatter as object).length > 0;
        const hasRemoveFm = Array.isArray(params.remove_frontmatter) &&
          (params.remove_frontmatter as unknown[]).length > 0;
        const hasFm = hasSetFm || hasRemoveFm;
    
        if (!hasAppend && !hasBody && !hasFm) {
          return {
            content: [
              {
                type: "text",
                text: "Provide 'append_text', 'body', 'set_frontmatter', or 'remove_frontmatter'.",
              },
            ],
            isError: true,
          };
        }
        if (hasAppend && hasBody) {
          return {
            content: [
              {
                type: "text",
                text: "Provide either 'append_text' or 'body', not both.",
              },
            ],
            isError: true,
          };
        }
      }
    
      try {
        const args = handler.buildArgs(params);
        let result: { stdout: string; stderr: string };
    
        // Check if this tool needs stdin piping
        const stdinData = handler.usesStdin?.(params) ?? null;
        if (stdinData !== null) {
          result = await execBcliWithStdinAndReauth(args, stdinData);
        } else {
          result = await execBcliWithReauth(args);
        }
    
        // Parse JSON output from bcli
        const stdout = result.stdout.trim();
        if (!stdout) {
          return {
            content: [{ type: "text", text: "Command completed successfully." }],
          };
        }
    
        // Validate it's JSON and pretty-print
        try {
          const parsed = JSON.parse(stdout);
          return {
            content: [
              { type: "text", text: JSON.stringify(parsed, null, 2) },
            ],
          };
        } catch {
          // If bcli returned non-JSON, pass it through
          return {
            content: [{ type: "text", text: stdout }],
          };
        }
      } catch (error) {
        const message =
          error instanceof BcliError ? error.message : String(error);
        return {
          content: [{ type: "text", text: message }],
          isError: true,
        };
      }
Behavior4/5

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

Annotations indicate idempotentHint and non-destructive, but the description adds crucial behavioral details: actions delete files (discard), move files (keep), and regenerate the index. This goes beyond annotations. No contradiction with readOnlyHint or destructiveHint.

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?

The description is three sentences, front-loading the purpose and actions. Every sentence adds unique information without redundancy. No wasted words.

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?

The description covers all required parameters and actions. For a tool with five parameters (two required) and no output schema, it explains the core workflow and side effects. However, it omits what the tool returns (e.g., success message or updated index), leaving an open question.

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 description coverage is 100%, so baseline is 3. The description adds value by explaining how group/subtag are used (e.g., subtag forms '#context/jira') and that summary is only for 'keep'. This enriches the schema definitions.

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?

The description clearly states the tool triages inbox files with three distinct actions: keep, push_to_bear, and discard. Each action is explained with specific effects (move, create note, delete). This distinguishes it from siblings like bear_context_push_to_bear, which only handles one action.

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?

The description explains when to use each action (e.g., 'keep' for moving with metadata, 'push_to_bear' for note creation). However, it does not explicitly state when not to use this tool versus alternative tools like bear_context_push_to_bear or bear_context_remove. The usage context is clear but lacks exclusion guidance.

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/KuvopLLC/better-bear'

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