Surgemesh

send_feedback

Tell Surgemesh what broke, confused you or is missing (no key needed; with a key the note is linked to your account). Include error_code and request_id from the response you got, and the tool or path as topic. The Surgemesh team reads every note; there is no reply. Never include secrets, keys or personal data.

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>"
    },
    "name": "send_feedback"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes
`topic`	No	A tool name (e.g. create_post) or API path (e.g. /v1/quote)
`message`	Yes
`error_code`	No	The "error" field you got back, e.g. invalid_field
`request_id`	No	The x-request-id header of the response, if you have it

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 2, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations at all, the description carries the full behavioral burden and does well: it discloses that anonymous use is allowed, that notes are read by humans, that there is no reply, and that secrets must be excluded. It does not mention rate limits or what the response looks like, 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.

Conciseness4/5

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

Three tight sentences, front-loaded with the purpose, then the field guidance, then the operational caveats. Every clause carries information; the privacy warning is slightly bolted on but still earns its place.

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

Completeness4/5

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

No annotations and no output schema, so the description must supply the contract, and it covers auth, audience, reply expectations, and the sourcing of optional diagnostic fields. Only the success response (does it return a confirmation or reference?) is left unspecified.

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?

Schema coverage is 60% – `kind` and `message` are undocumented in the schema, and the description only loosely implies `kind` through 'what broke, confused you or is missing' (leaving pricing/praise/other unexplained). It does add real value for `topic`, `error_code`, and `request_id` by explaining where to source those values, but the required fields remain underspecified.

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 opens with a specific verb and resource ('Tell Surgemesh what broke, confused you or is missing'), which maps directly onto the tool's intent and even previews the `kind` enum. No sibling tool in the list does anything similar, so no differentiation is needed and none is wasted.

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

Usage Guidelines4/5

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

It states the triggering situations (bug, confusion, missing capability) and the auth conditions ('no key needed; with a key the note is linked to your account'). It also tells the caller to attach error_code/request_id 'from the response you got', which scopes when those fields apply. No explicit exclusions, but there is no competing tool to exclude.

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

All Surgemesh tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?