All notes under a folder (or tag) in one blob: rules, _about.md, _ai.md, context and decisions first, closed sub-units skipped. The header names the notes that did NOT fit: read_file those you need.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | ||
| path | No | ||
| max_chars | No | ||
| workspace | No | Usually omit; else brain id (as in search hits), 'mine', or owner name/email. |
Changes observed during successful MCP inspections.
Input schema / properties / workspace / descriptionPrevious value: -"Brain to act on: its id, «mio» (yours), or the owner's name/email as shown by search. Usually OMIT it: a path that already lives in one brain is found there, for reads and writes alike. Pass it only when the tool tells you to (a NEW branch, or one that exists in several brains) — with the brain the user named; when they were not explicit ASK THEM. A brain where the branch does not exist is refused even if you name it."New value: +"Usually omit; else brain id (as in search hits), 'mine', or owner name/email."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, and the description still adds real behavior: deterministic ordering (rules, _about.md, _ai.md, context and decisions first), exclusion of closed sub-units, and the fact that the header enumerates notes that did not fit. It does not explain how the truncation is bounded, which keeps it short of a 5.
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 dense sentences with no filler; the most decision-relevant facts (what you get, ordering, the overflow escape hatch) come first. The telegraphic style borders on cryptic but never wastes a clause.
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 zero-required-param, read-only aggregator with no output schema, the description covers ordering, skipping, and the overflow header, which is the core of what an agent needs. Gaps remain on path/tag interaction and on how truncation interacts with max_chars, so it is adequate rather than complete.
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 25% (just the workspace param), so the description must compensate, and it partly does: it clarifies the folder-vs-tag duality implied by the path and tag params and hints that output size is bounded (relevant to max_chars). It does not state whether path and tag are mutually exclusive, precedence rules, or what max_chars defaults to.
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 resource ('all notes under a folder (or tag)') and the delivery form ('in one blob'), which distinguishes it from the single-note read_file sibling it explicitly names. The verb is implied rather than stated and the phrasing is compressed, but an agent can identify the operation.
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?
It names read_file as the follow-up for material that was trimmed ('read_file those you need'), which is a useful conditional routing hint. However it never says when to prefer this bulk load over siblings like list_files, files_by_tag, or find_notes, so the primary selection guidance is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.