Skip to main content
Glama
AdrianV101

obsidian-pkm

by AdrianV101

vault_read

Read markdown files from an Obsidian vault. Supports pagination via heading, line range, chunk, or tail sections, with automatic outline for large files.

Instructions

Read the contents of a markdown file from the vault. Supports pagination: read a single section by heading, last N lines, last N heading-level sections, chunk number, or line range. Files exceeding ~80k characters auto-redirect to peek data (file structure/outline) unless a pagination param or force=true is specified. Paths in this tool's output are formatted as markdown links [vault-relative-path.md](obsidian://...) so users can Cmd/Ctrl-click to open in Obsidian. Preserve the link form when relaying paths to the user; pass only the bracket text (e.g. 01-Projects/Foo/note.md) to other vault tools' path arguments, never the full markdown link.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesPath relative to vault root (supports short names, e.g. 'devlog')
tailNoReturn the last N lines of the file. Frontmatter is always prepended.
chunkNoRead a specific chunk of the file (1-indexed). Each chunk is ~80k characters. Use vault_peek to see total chunks.
forceNoBypass auto-redirect for large files. WARNING: only use when full content is essential, as large files degrade model performance. Hard-capped at ~400k chars (~100k tokens).
linesNoRead a range of lines from the file (1-indexed, inclusive).
headingNoRead only the section under this heading (exact match, case-sensitive). Returns heading line + content until next same-or-higher-level heading.
section_levelNoHeading level for tail_sections (1=`#`, 2=`##`, etc). Default: 2.
tail_sectionsNoReturn the last N sections at the specified heading level. Frontmatter is always prepended.
Behavior5/5

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

With no annotations provided, the description carries full burden and delivers. It discloses auto-redirect behavior for large files, a hard cap of ~400k chars, performance degradation warnings for force, and the markdown-link output format. It also instructs the agent on how to transform paths before passing to other tools, adding operational nuance beyond a simple read.

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 a compact, front-loaded block of four sentences. Each sentence earns its place: purpose, pagination capabilities, auto-redirect behavior, and path-link handling. No filler or redundant restatement of the schema.

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

Completeness5/5

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

Despite having no output schema, the description explains what data is returned (file contents or peek structure on redirect), how paths are formatted, and the performance envelope. The auto-redirect resolution and force cap address edge cases, making the description complete for a tool of this complexity.

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 coverage is 100%, so baseline is 3, but the description adds semantic grouping by summarizing the pagination modes (heading, tail, sections, chunks, line range) and links them to the auto-redirect threshold. The force parameter's warning and the chunk param's reference to vault_peek go beyond the raw schema, enriching parameter understanding.

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 opens with 'Read the contents of a markdown file from the vault', a specific verb+resource pairing that clearly distinguishes the tool from siblings like vault_peek, vault_search, or vault_write. It further elaborates on pagination modes, reinforcing what the tool does and its scope.

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

Usage Guidelines5/5

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

Guidance is explicit: large files auto-redirect to peek data unless a pagination param or force=true, and force is discouraged unless essential. It names vault_peek as an alternative for browsing chunks and outlines when to use pagination params, giving clear when-to-use vs when-not-to-use context.

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/AdrianV101/obsidian-pkm-plugin'

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