mysharedbrain

by hampusadamsson

Overview Schema Source Related Servers Discussions Admin

Python

Local

Give Feedback

give_feedback

Send a correction, missing note, or request into a review queue; the librarian applies approved feedback to your vault.

Instructions

Teach the brain: queue feedback the librarian applies later.

This is the self-learning loop — the single most important tool here. Either hand over the information itself (a correction, a fact, content for a missing note) or say where to get it (a source to check, what is missing). The entry lands in the capture queue as pending and the librarian reviews it (applied/approved/rejected) before the vault changes.

"kind is one of: edit | missing | request | question.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`body`	Yes
`kind`	Yes
`note_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 19, 2026
- changedOutput schema / additionalProperties
```
Previous value: -{
-  "type": "string"
-}New value: +true
```
First observedv0.1.0Sep 12, 2026

TDQS

A3.6/5.0

Behavior4/5

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

The description transparently discloses that entries are queued as pending and reviewed (applied/approved/rejected) before vault changes, which is a key behavioral trait beyond what the schema shows. It does not mention permissions, error handling, or other side effects, but given no annotations are provided, the description covers the most critical aspect of delayed application.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear opening metaphor, a purpose explanation, and a kind list. It is front-loaded with the key idea and remains readable. It is slightly verbose but not excessively so, earning a strong score.

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

Completeness3/5

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

The description covers the purpose, the queue/review flow, and kind values, but omits note_id semantics and any additional context like prerequisites or failure modes. Since an output schema exists, return values are not needed, but the description could be more complete in explaining all parameters and edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explains 'kind' as one of edit|missing|request|question, and 'body' as the information or source. However, it does not explain 'note_id', leaving it ambiguous. With 0% schema description coverage, the description should cover all parameters, so this partial coverage is a gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: queue feedback for the librarian to apply later. It identifies the verb+resource ('queue feedback') and explains the self-learning loop. However, it does not explicitly differentiate from sibling tools like update_note or create_note, so it falls short of a perfect score.

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

Usage Guidelines3/5

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

The description provides context that this is for feedback that is reviewed before vault changes, implying it is for corrections/facts rather than direct modification. However, it does not explicitly state when to use this tool versus alternatives, nor does it name specific siblings or provide exclusion criteria. The guidance is implicit rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.