gemini-cli-bridge

Overview Schema Source Related Servers Discussions Admin

Gemini Prompt With Memory

gemini_prompt_with_memory

Injects memory_paths as high-priority context, then runs Gemini CLI non-interactively so project conventions and system memory guide prompts.

Instructions

Inject memory_paths as high-priority context, then run non-interactively.

memory_paths: authoritative project/system memory (e.g., GEMINI.md, conventions).
attachments: additional files/dirs injected as @path.

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": {
      "prompt": "<prompt>"
    },
    "name": "gemini_prompt_with_memory"
  }
}

Input Schema

Name	Required	Default
`yolo`	No
`model`	No	gemini-2.5-pro
`prompt`	Yes
`timeout_s`	No
`extra_args`	No
`attachments`	No
`include_dirs`	No
`memory_paths`	No
`approval_mode`	No
`checkpointing`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.2Oct 20, 2026

TDQS

C2.7/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that memory_paths override as 'high-priority context' and that the run is non-interactive, which is useful. However, it is silent on the safety-relevant parameters yolo, approval_mode, checkpointing, and timeout_s, so the agent cannot gauge autonomy or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight lines that front-load the core action, with the parameter notes as crisp bullets. No filler. Slightly terse given the parameter breadth, but well-structured.

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

Completeness2/5

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

An output schema exists so return values need not be described. But for a 10-parameter tool with zero schema coverage and no annotations, covering only 2 parameters leaves the definition materially incomplete, especially around the autonomy controls (yolo, approval_mode) an agent would need before invoking it.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must carry parameter meaning. It explains only memory_paths and attachments, leaving 8 of 10 parameters (yolo, approval_mode, model, timeout_s, extra_args, include_dirs, checkpointing, prompt) completely undocumented in both schema and description.

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 compound action (inject memory_paths as high-priority context, then run the prompt non-interactively) on a named resource. The 'with_memory' framing distinguishes it conceptually from the plain gemini_prompt sibling, but the description never names that sibling explicitly to confirm the distinction.

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

Usage Guidelines2/5

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

The description clarifies that memory_paths are treated as authoritative context, which hints at when this tool is preferred, but gives no explicit when-to-use/when-not guidance and never contrasts it with gemini_prompt or gemini_prompt_plus. Nothing tells the agent which sibling to pick.

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