Skip to main content
Glama
RawTree MCP Server

RawTree MCP Server

Official
by rawtreedb

Submit Feedback

submit-feedback

Report bugs, confusing errors, unclear behavior, missing documentation, or blocking questions to RawTree by describing what you tried, what happened, and what you expected.

Instructions

While working with RawTree through this MCP connection, use submit-feedback to report bugs, inconsistencies, confusing errors, unclear behavior, missing documentation, or questions that prevent you from understanding how to proceed. This tool is for agents as well as humans. Set actor_type to agent for issues you discover or observations you originate. When a user asks you to send their feedback, set actor_type to human, even though you call the tool. Describe what you tried, what happened, and what you expected; put relevant tool names, error codes, or reproduction details in extra. Do not include credentials or private data. Avoid repeated reports of the same issue during a task. Submission stores feedback; it does not resolve the issue or guarantee a reply. Do not automatically retry an uncertain result because submissions are not deduplicated.

Uses this connection's API URL and credentials. Works before an organization exists. API keys and workload tokens supply their bound organization and cluster. With user credentials, optional organization_id and cluster_id are UUIDs; a cluster determines its organization. Configured organization/cluster names and database defaults are not substituted for these IDs. Explicit scope must be accessible to the caller. Returns { id, created_at } after successful storage.

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": {
      "message": "<message>",
      "category": "<category>",
      "actor_type": "<actor_type>"
    },
    "name": "submit-feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
extraNoAdditional JSON object with relevant tool, command, error, or reproduction details. Nested JSON values are supported.
messageYesWhat you tried, what happened, and what you expected.
categoryYesbug for defects or inconsistencies; feature_request for improvements; question for unclear behavior; other for remaining feedback.
actor_typeYeshuman when the user asks to send their feedback; agent for the agent's own observations. The tool caller or credential does not determine authorship.
cluster_idNoOptional cluster UUID; inferred from scoped credentials.
organization_idNoOptional organization UUID; inferred from scoped credentials or the supplied cluster.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.6

TDQS

A4.6/5.0
Behavior4/5

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

Goes well past the annotations by disclosing that submissions are stored but not deduplicated (consistent with idempotentHint=false), that the tool does not resolve the issue or guarantee a reply, that it works before an organization exists, and how scope is inferred from API keys, workload tokens, or user credentials. The one gap is that 'not deduplicated' is stated but the practical consequence for a retried request is only implied rather than spelled out.

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?

Front-loaded with purpose before routing rules, and nearly every sentence carries an actionable constraint. It is on the long side for a six-parameter tool and repeats the actor_type rule from the schema, which costs a little density without causing confusion.

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?

Covers the full surface an agent needs: what to submit, how to choose the actor and category, what not to include, retry behavior, scoping semantics for the two UUID parameters, and the return value ('{ id, created_at } after successful storage') despite there being no output schema. Nothing material is left for the agent to infer before calling.

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 description coverage is already 100%, so the baseline is 3, but the description adds real meaning beyond the schema: organization_id/cluster_id are UUIDs only, a cluster determines its organization, and 'configured organization/cluster names and database defaults are not substituted for these IDs' — a nuance absent from the schema. It also directs what belongs in 'extra' (tool names, error codes, reproduction details) and restates the actor_type rule, though the actor_type guidance largely duplicates the schema's own description.

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?

Opens with a specific verb+resource ('use submit-feedback to report bugs, inconsistencies, confusing errors, unclear behavior, missing documentation, or questions') and enumerates exactly which artifacts qualify. No sibling tool covers feedback submission, so there is no ambiguity to resolve, and the tool is trivially distinguishable from the create/delete/list cluster of siblings.

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 (issues that prevent you from proceeding), when-not-to-use ('avoid repeated reports of the same issue during a task'), and two hard exclusions ('do not include credentials or private data', 'do not automatically retry an uncertain result'). It also resolves the authorship ambiguity with a concrete decision rule: actor_type=agent for the agent's own observations, human when the user asks you to send theirs.

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