List or read notebook cells by style, position, and content to locate inputs for evaluation.
List or read cells of an open notebook. Use style to filter (e.g. 'Input'). Cell indices are positions in the document and are what evaluate_cells takes.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| style | No | ||
| offset | No | ||
| notebook | No | ||
| include_content | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are attached, so the description carries the full burden of disclosure. It implies a read operation ('list or read') and discloses that indices map to evaluate_cells input, which is useful behavioral context. But it does not reveal pagination semantics implied by limit/offset defaults, what happens with notebook=null, or the output shape. Partial disclosure with no contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with the purpose front-loaded and the sibling-routing hint placed at the end. No filler or redundant phrasing, though the guidance is thin relative to the tool's parameter count.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema covers return values, but the tool has five parameters with no schema docstrings and zero annotation coverage. The description omits notebook-selection semantics, pagination, and content flags, so a correct call is under-specified for an agent. Incomplete given the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate by explaining the five parameters, yet it only addresses style (with the 'Input' example) and introduces the index concept. limit, offset, include_content, and notebook remain unexplained, leaving an agent to guess at pagination, content-inclusion, and notebook-selection behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb-resource pair ('List or read cells of an open notebook') and adds the clarifying fact that cell indices are positions in the document, linking to the sibling evaluate_cells. This distinguishes it from notebook-management siblings like notebooks and edit_cells, though the dual 'list or read' phrasing leaves scope slightly ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides one routing signal — that the returned indices are what evaluate_cells consumes — which indirectly tells an agent this tool is the source for cell index data. However, it never explicitly states when to prefer this tool over siblings (e.g., edit_cells, render) or when not to use it, and there are no exclusions or preconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.