Skip to main content
Glama

Send feedback

feedback_send

Tell Known's team what got in the way while you worked with Known: a tool that failed or answered wrongly, one you needed and Known does not have, a tool or doc whose words misled you, or an idea that would have made the work easier. Known's team reads every note; nothing comes back but a receipt. Send one note for each problem, when you meet it or at the end of the task, never for the person's own requests or questions, and never with their content: describe what you were doing and what Known did, not what the pages, records or files say.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>",
      "message": "<message>",
      "org": "<org>"
    },
    "name": "feedback_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgYesslug of the organization you were working in. Required on every call, even when only one organization is listed; a path never names it.
refNoThe reference a failed call answered with ("reference …"), when there is one.
kindYesbug: a tool failed or answered wrongly; missing: a tool or option you needed is not there; confusing: a tool, its answer or Known's docs misled you; idea: something that would have made the work easier.
aboutNoThe tool, CLI command or doc it is about (wiki_edit), when there is one.
messageYesWhat you were trying to do, what Known did, and what would have helped. Plain words; no content from the organization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, openWorldHint=false and destructiveHint=false, so the write-without-external-side-effect profile is already structured. The description adds genuinely useful context beyond that: the team reads every note, only a receipt comes back, and content must be excluded. It does not cover rate limits, whether notes are attributed, or what the receipt contains, which keeps this at a solid 3 rather than higher.

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 purpose and the four categories are front-loaded, then the guidance and the confidentiality constraint follow in logical order. It is dense but nearly every clause carries a distinct instruction; the enumeration of categories is somewhat redundant with the kind enum but still aids selection.

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?

For a five-parameter write tool with full schema coverage and no output schema, the definition covers trigger, exclusions, content rules, and what the caller gets back. An agent has everything needed to decide to call it and to compose a correct message.

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 the baseline is 3, but the description earns an increment by explaining the purpose of the message field's constraint: describe what you were doing and what Known did, not what the pages, records or files say. That gives the agent a rule for what to write, not just a length limit.

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 states a specific verb and resource: send a note to Known's team about problems encountered while working. It enumerates the four problem categories (failed tool, missing tool, misleading docs, idea) and maps them to the enum kinds, so an agent can tell this apart from every sibling tool in the list, none of which report problems.

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?

Explicit when-to-use: one note per problem, at the moment it is met or at the end of the task. Explicit when-not-to: never for the person's own requests or questions, and never including their content. This is the rare definition that gives both the trigger and the exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources