Gemini Notebook by Chryzalide (agy-gemini-notebook-plugin)

notebook_invoke

Invoke a Gemini Notebook by ID, alias, or title to ground a task. Provide a question for cited answers, or omit it to retrieve notebook summary, topics, and sources.

Instructions

Invoke a Gemini Notebook by ID, workspace alias, or title to ground the current task.

- If `question` is provided: executes a grounded query against the target notebook and returns
  the synthesized answer, inline citations, and follow-up suggestions.
- If `question` is omitted: fetches the notebook's metadata, AI summary, suggested topics,
  and source list so the agent can immediately inspect and use the notebook context.

Input Schema

Name	Required	Default
`engine`	No	auto
`target`	No
`question`	No
`workspace_dir`	No
`include_sources`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 25, 2026

TDQS

B3.2/5.0

Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does describe what each mode returns (synthesized answer, citations, follow-ups; metadata, summary, topics, sources). That is meaningful behavioral detail, but it says nothing about read-only vs mutating nature, permission/auth requirements, or rate limits, which are the gaps annotations would normally cover.

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?

Front-loaded with the core action, then cleanly separated into two conditional bullets. Nearly every sentence earns its place, with only minor verbosity in the return-value enumeration.

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

Completeness3/5

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

An output schema exists, so return shapes needn't be documented, yet three of five parameters have no explanation in schema or description, and the tool's permission/side-effect profile is unstated. Adequate for the dual-mode behavior but not complete for a zero-coverage five-parameter tool.

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% for five parameters. The description clarifies only `question` behavior and implicitly maps `target` to 'ID, workspace alias, or title', but `engine`, `workspace_dir`, and `include_sources` are entirely unexplained anywhere, which is a substantial gap at this coverage level.

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?

Names a specific verb and resource ('Invoke a Gemini Notebook') and clarifies the identifying keys (ID, workspace alias, title). It does not distinguish this from close siblings like notebook_query or notebook_get, so an agent cannot be fully certain which sibling is the right call without reading both schemas.

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 two-bullet branch explains when the tool behaves one way versus the other (question present vs omitted), which is useful internal routing guidance. However, it offers no comparison to alternatives such as notebook_query or notebook_get, leaving the agent to guess whether invoking is preferred over querying.

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