Smartpress

Send feedback to Smartpress

send_feedback

Send the user's feedback to the Smartpress team: a problem they ran into, a suggestion, or praise.

Rules:

Call this ONLY when the user asks to send feedback, report a problem, or pass on praise. Never call it on your own after an error; you may offer it.
Before calling, show the user what you'll send (type, and the message) and get their yes.
Put the user's own words in "message". Leave out payment details, passwords and anything they asked you not to share.
Pass the ids of what the conversation was working on (product, configuration, artwork, proof), and for a failed tool call its name and error, so the team can find it.

Afterwards, give the user the reference (e.g. FB-3F9K). Nobody replies through this channel; for help with an order, point them to Smartpress customer support.

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": {
      "type": "<type>",
      "message": "<message>"
    },
    "name": "send_feedback"
  }
}

Input Schema

Name	Required	Description
`type`	Yes	"problem" for something that went wrong, "suggestion" for an idea, "praise" for something that worked well.
`message`	Yes	The user's feedback in their own words. Quote or closely follow what they said; don't summarize it into your words.
`proofId`	No	The proof being discussed, when there is one.
`severity`	No	Problems only, required for a problem: "blocked" = it stopped the user from ordering, "workaround" = they got around it, "cosmetic" = minor. Leave out for a suggestion or praise.
`productId`	No	The product being discussed, e.g. "SLS_12", when there is one.
`relatedTool`	No	For a problem with a failed tool call: that tool's name.
`contactEmail`	No	Only when the user offers an email address for a reply.
`errorMessage`	No	For a problem with a failed tool call: the error it returned.
`fileSessionId`	No	The uploaded artwork being discussed, when there is one.
`productConfigSessionId`	No	The configuration being discussed, when there is one.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 26, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that nothing is written back to the user through this channel, that a reference id is returned, that payment details and passwords must be redacted, and that confirmation is required before sending. Annotations only say it is a non-idempotent, non-destructive, closed-world write; the description supplies the actual workflow and privacy behavior.

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

Conciseness5/5

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

Front-loaded with the one-line purpose, then four short rules followed by the post-call instruction. Every sentence carries an operational instruction; no filler or restated schema text.

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 10-parameter write tool with no output schema, it covers the full lifecycle: when to call, consent and redaction before sending, which contextual ids to attach, and what to tell the user afterwards (reference id, support redirect). Nothing an agent needs to call it safely 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 schema already documents every field and its enums, setting the baseline at 3. The description adds real routing guidance the schema does not: put the user's own words in message, and pass the ids of whatever the conversation was working on (product, configuration, artwork, proof) plus relatedTool/errorMessage for a failed call. It leaves contactEmail and severity only implicitly covered, so it stops short of full marks.

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 the user's feedback to the Smartpress team) plus the three content categories it covers. No sibling tool does anything similar, and the description makes that obvious by naming the channel and audience.

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 explicit trigger conditions (user asks to send feedback, report a problem, pass on praise) and an explicit exclusion (never call on your own after an error, but may offer). It also adds a pre-call consent gate, which is a usage rule rather than a restatement of the schema.

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

All Smartpress 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?