List, read, and normalize project source files and PDFs into Markdown, providing accessible documentation for AI agents.
Source files/PDFs: list, read, normalize to Markdown.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | ||
| action | No | normalize=Markdown. | list |
| pattern | No | **/* | |
| category | No | ||
| max_chars | No | ||
| overwrite | No |
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | ||
| guidance | No | ||
| nextAction | Yes | ||
| resultText | No |
Changes observed during successful MCP inspections.
v2.9.0Input schema / properties / action / descriptionPrevious value: -"list=sources; read=open; normalize=Markdown."New value: +"normalize=Markdown."Output schema / additionalPropertiesRemoved value: -truev2.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal destructiveHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds behavioral context by naming the normalize-to-Markdown transformation, though it does not disclose that normalization may overwrite files or otherwise modify state; that nuance is left to the 'overwrite' parameter.
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?
The one-line description is front-loaded with the resource and actions and contains no filler. It is appropriately sized for a high-level summary, even though the underlying tool has more parameters than the description addresses.
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?
For a six-parameter tool with low schema description coverage and a destructive hint, a single sentence is under-specified. It does not explain parameter relationships, overwrite behavior, path/pattern/category usage, or when this tool fits among the eight siblings; the existence of an output schema mitigates only the return-value gap.
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 only 17%, and the description does not compensate: it barely maps to the 'action' enum and never explains path, pattern, category, max_chars, or overwrite. Without reading the schema, an agent cannot tell what most parameters control.
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?
The description names concrete operations 'list, read, normalize' and a specific resource type, 'Source files/PDFs,' so an agent knows exactly what domain this tool covers. This also differentiates it from sibling tools like knowledge_ingest, knowledge_code, and knowledge_document, which target different resources or workflows.
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?
The resource phrase and action list imply when to use the tool (working with source files/PDFs and producing Markdown), but the description never explicitly says when to prefer it over the sibling knowledge tools or when not to use it. There are no exclusions or alternative-routing hints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.