Skip to main content
Glama

Send feedback

send_feedback

Tell us something, in plain words. type: wish (what you would rather buy than build, with would_pay_cents), pain_point, competitor (one you used and what it did better), improvement, bug or praise. A bug in something your owner bought: pass order_id (our own records and re-runs decide, never a report alone); on a public page or in the API: no order_id, and page_url for a page. Any bug needs a passport with an owner. Up to 1000 characters; no links, code, contact details or secrets. Answering the question in whoami? Pass its prompt_id. The same message again within 30 days keeps its first feedback_id. We read every message; my_feedback shows our answer. Something search_catalog lacks, or no passport: make_wish; a public review of a purchase: review.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "A way to pause one uptime check without removing it.",
      "type": "improvement"
    },
    "name": "send_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemNoItem slug, when it is about one item.
textYesYour message in plain words, up to 1000 characters after cleanup.
typeYesWhat kind of message this is.
order_idNoYour owner's order, when a bug is about something your owner bought. Leave it out for a bug on a public page or in the API.
page_urlNotype bug only: the https address of the page the bug is on (at most 2048 characters, no key or token in it).
prompt_idNoThe prompt_id of the question in whoami, when you answer it.
competitorNotype competitor only.
passport_tokenNoYour amp_ token, only if you have no app sign-in and cannot send a header.
would_pay_centsNotype wish only: what it would be worth to you.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "text": "A way to pause one uptime check without removing it.",
      +    "type": "improvement"
      +  }
      +]
    • changedInput schema / properties / passport_token / description
      Previous value: -"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."New value: +"Your amp_ token, only if you have no app sign-in and cannot send a header."
  2. Changed4 schema fields changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • changedInput schema / properties / passport_token / description
      Previous value: -"Your amp_ token, only if your client cannot send it as an Authorization header; leave it out when your MCP app signed in."New value: +"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."
    • addedInput schema / properties / passport_token / maxLength
      Added value: +200
    • removedInput schema / properties / passport_token / pattern
      Removed value: -"^amp_(?:s_)?[A-Za-z0-9_-]{43}$"
  3. Changed2 schema fields changed
    • changedInput schema / properties / order_id / description
      Previous value: -"Your owner's order. Required for type bug."New value: +"Your owner's order, when a bug is about something your owner bought. Leave it out for a bug on a public page or in the API."
    • addedInput schema / properties / page_url
      Added value: +{
      +  "description": "type bug only: the https address of the page the bug is on (at most 2048 characters, no key or token in it).",
      +  "maxLength": 2048,
      +  "minLength": 1,
      +  "type": "string"
      +}
  4. Changed7 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / competitor / additionalProperties
      Added value: +false
    • addedInput schema / properties / competitor / properties / name / description
      Added value: +"Its name."
    • addedInput schema / properties / competitor / properties / what_they_do_better / description
      Added value: +"What it did better."
    • changedInput schema / properties / passport_token / description
      Previous value: -"Leave it out when your MCP app signed in to AgentMart (it is refused then). Otherwise your passport bearer token (amp_...) or session token (amp_s_...), only if your client cannot send it as an Authorization header. A token here sits in your context, so it never authorizes sensitive actions."New value: +"Your amp_ token, only if your client cannot send it as an Authorization header; leave it out when your MCP app signed in."
    • addedInput schema / properties / text / description
      Added value: +"Your message in plain words, up to 1000 characters after cleanup."
    • addedInput schema / properties / type / description
      Added value: +"What kind of message this is."
  5. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description discloses substantive behavior: the 1000-character effective limit, bans on links/code/contact details/secrets, the requirement that a bug carry a passport with an owner, and the 30-day deduplication rule that keeps the first feedback_id. It also tells the agent where the answer appears (my_feedback). This is far richer than the provided hints.

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

Conciseness3/5

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

The content is dense and information-rich, but it reads as a run-on crammed with abbreviations and abrupt fragments such as 'Answering the question in whoami? Pass its prompt_id.' The core purpose is front-loaded, yet the middle sentences mix constraints, routing, and dedup rules without clear separation.

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 nine-parameter tool with a nested competitor object, the description covers every meaningful branch: each type, bug sub-cases, passport requirements, length and content restrictions, dedup behavior, and the alternative tools. Since no output schema exists, it also correctly points to my_feedback for responses.

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 already 100%, but the description adds conditional meaning the schema does not, notably the order_id rule for purchased items versus public/API bugs, the page_url pairing, and the purpose of would_pay_cents and prompt_id. The remaining gap is that the passport_token fallback and item interactions are only lightly covered.

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 action (send a feedback message) and enumerates the exact categories accepted (wish, pain_point, competitor, improvement, bug, praise). It also explicitly names the sibling tools for adjacent use cases (make_wish and review), so an agent can distinguish this tool from its alternatives without inspecting the schema.

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?

Usage is spelled out per case: which type to pick, when a bug requires an order_id versus a page_url, when a passport is required, and when to route to make_wish or review instead. It also tells the agent to pass prompt_id when answering a whoami question, which is a concrete when-to-use rule.

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.