Units (folders with _about.md): path, type, status, notes, last change, open sub-units. Closed ones only with all=true.
| Name | Required | Description | Default |
|---|---|---|---|
| all | No | ||
| type | 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, openWorldHint=false, destructiveHint=false). The description goes beyond them by disclosing the default filtering rule (closed units excluded unless all=true) and the shape of returned fields, which is real behavioral context.
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 telegraphic sentences, no filler; the resource definition and its returned fields are front-loaded, with the filtering caveat last. Density is high but a few fragments ('open sub-units', 'closed ones') are slightly cryptic.
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?
With no output schema, the field list carries the return-value burden reasonably well, and the default-exclusion rule is stated. However, nothing covers the undocumented `type` parameter, pagination/size limits, or what values 'status' and 'type' can take.
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 coverage is only 33%, and the description compensates for one gap by explaining the `all` flag's effect. The `type` parameter remains undocumented in both description and schema, so compensation is partial rather than complete.
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 defines the resource concretely ('Units (folders with _about.md)') and enumerates the fields it returns, which is far more than the bare tool name offers. It does not name or contrast with the nearest siblings (list_files, list_tags, list_workspaces), so it falls short of a 5.
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?
'Closed ones only with all=true' gives one explicit conditional that governs behavior, but there is no overall when-to-use guidance and no routing to alternatives like list_files for plain files. Usage is implied rather than stated.
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.