Skip to main content
Glama
Sign In

Close Knit

by com.getcloseknit
OverviewDiscussionsAdmin

Send feedback

send_feedback

Send feedback about Close Knit to the team: a bug, missing or wrong data, an idea, or what worked. Call it only after the user agrees: show them the message first. Describe the product and what happened, never the person: no names, contact details, addresses, family, budget or other personal circumstances. Kept 12 months, e-mail addresses and phone numbers removed; no reply channel: the answer gives an id, the changelog names ids fixed. Ratings sent with rate_answer: 90 days.

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

NameRequiredDescriptionDefault
kindYes[option] bug = a tool failed or misbehaved; missing-data / wrong-data = an answer lacked or got a fact wrong; idea = something to add; praise = what worked well.
toolsNo[input value] The Close Knit tools it is about, e.g. ['find_areas'].
clientNo[input value] The AI client, e.g. 'claude.ai'.
ratingNo[input value] How useful Close Knit was, 1-5, if the user said.
messageYes[input value] What happened or what would help, in a few sentences: the product, never the person. No names, contact details, addresses, family or money circumstances.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / client / description
      Previous value: -"The AI client, e.g. 'claude.ai'."New value: +"[input value] The AI client, e.g. 'claude.ai'."
    • changedInput schema / properties / kind / description
      Previous value: -"bug = a tool failed or misbehaved; missing-data / wrong-data = an answer lacked or got a fact wrong; idea = something to add; praise = what worked well."New value: +"[option] bug = a tool failed or misbehaved; missing-data / wrong-data = an answer lacked or got a fact wrong; idea = something to add; praise = what worked well."
    • changedInput schema / properties / message / description
      Previous value: -"What happened or what would help, in a few sentences: the product, never the person. No names, contact details, addresses, family or money circumstances."New value: +"[input value] What happened or what would help, in a few sentences: the product, never the person. No names, contact details, addresses, family or money circumstances."
    • changedInput schema / properties / rating / description
      Previous value: -"How useful Close Knit was, 1-5, if the user said."New value: +"[input value] How useful Close Knit was, 1-5, if the user said."
    • changedInput schema / properties / tools / description
      Previous value: -"The Close Knit tools it is about, e.g. ['find_areas']."New value: +"[input value] The Close Knit tools it is about, e.g. ['find_areas']."
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing retention (12 months), that e-mail addresses and phone numbers are stripped, that there is no reply channel, and that the response returns an id surfaced in the changelog. Those facts matter for a non-readOnly submission tool; the only gap is that it doesn't say where feedback is stored or whether it can be withdrawn.

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 the purpose, then consent, then privacy rules, then retention and the routing note -- a sensible order with no filler. The final two sentences are clipped to the point of being telegraphic ('Ratings sent with rate_answer: 90 days.'), costing some readability.

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?

An output schema exists, so return values need not be described, and the definition covers the remaining agent-relevant concerns: consent, privacy constraints, retention period, and the no-reply-channel expectation. Nothing an agent needs to call this correctly is missing.

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; the description still adds meaning by imposing a content policy on the message ('describe the product and what happened, never the person: no names, contact details, addresses, family, budget'), which constrains what an agent should put in that field. The tools/client/rating parameters are left entirely to the schema.

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?

States a specific verb and resource ('Send feedback about Close Knit to the team') and enumerates the kinds of feedback covered (bug, missing or wrong data, idea, praise), which is enough for an agent to distinguish it from the query/search 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?

Gives an explicit precondition ('Call it only after the user agrees: show them the message first') and routes ratings to a named alternative ('Ratings sent with rate_answer'), so the when-to-use and when-not-to-use boundaries are both stated.

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

All Close Knit toolsInspect
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