Skip to main content
Glama

Tell CommerceBook what would help

commercebook_feedback_create

Tell CommerceBook what happened and what would help, with a key or without one, or post and reply on the feedback board. Send a note when a tool did not do what you needed. A person at CommerceBook reads every note. Actions (the activity each needs):

  • send (no key): a note on what happened and what would help, rating 1 to 5. It answers the note’s id, whether the note is recorded against a key, and the next step.

  • post (needs a key with Orders: Can act): a new board post under your person’s name. It answers the new post with its id, title, status (open), votes and replies.

  • reply (needs a key with Orders: Can act): a reply to a board post. It answers the reply’s id, the post’s id and reply count, and how many people CommerceBook emailed. Send action and its arguments. Without action it runs send. With a key, or with ?role=buyer, seller, warehouse or all, the server also lists the separate tools that list, order, pay and ship.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "commercebook_feedback_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoFor post, reply. The text, up to 4,000 characters.
pageNoFor post. The page or the tool it is about, for example /warehouse/leads.
aboutNoFor send. A tool name (for example commercebook_buy_read action shipping_quote) or a page (for example /feeds).
titleNoFor post. The title of the post, up to 120 characters.
actionNoThe action to run (send when left out).send
ratingNoFor send. How well it went, from 1 (badly) to 5 (well).
post_idNoFor reply. The id of a post on the feedback board.
what_happenedNoFor send. What you tried and what happened, in plain words.
what_would_helpNoFor send. What would have made it work, or made it easier.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false), the description discloses the permission tier each write action requires, that 'A person at CommerceBook reads every note', and the exact payload each action returns (note id and recording status for send; post id, title, status, votes, replies for post; reply id, post id, reply count, and email count for reply). It also discloses a non-obvious side effect: with a key or ?role=, the server additionally lists the list/order/pay/ship tools.

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 statement is front-loaded, and the three actions are broken into a scannable bulleted list with requirements and return values per bullet. It is somewhat dense and the closing sentence about role-based tool listing sits awkwardly at the end, but no sentence is pure filler.

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 9-parameter, three-action, non-idempotent write tool with no output schema, the description covers what an agent needs: the default action, permission requirements per action, and the return shape for each action. Nothing essential is left to inference, and the disclosure of the role-based tool listing prevents surprise from an unexpected response field.

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 description coverage is 100%, so the schema already documents every parameter including its action scoping ('For send', 'For post', 'For reply'). The description largely restates that mapping (rating 1-5 for send, body for post/reply) rather than adding new semantics such as constraints, defaults, or interactions between fields. Baseline 3 applies since the schema carries the real load.

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 uses a specific verb-plus-resource framing ('Tell CommerceBook what happened and what would help') and then decomposes the tool into three named actions ('send', 'post', 'reply'), each with its own scope. None of the sibling tools (account_start, capabilities, market, start_read, tool_search) overlap with feedback submission, so the tool is unambiguously distinguishable.

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 gives an explicit trigger ('Send a note when a tool did not do what you needed') and spells out prerequisites per action ('post (needs a key with Orders: Can act)', 'reply (needs a key with Orders: Can act)'). It also states the default when no action is supplied. What is missing is any when-not guidance or explicit routing away from an alternative means of contact.

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.