Proxy

Send Feedback

submit_feedback

Send the user's feedback about Proxy to the Proxy team. Call when the user asks to send feedback, complains about a result, or praises one, or needs ad or competitor-advertising data no tool here covers (category missing_tool). Offer it after a tool fails twice. Also call it on your own (reporter=agent), without asking the user, when a Proxy tool returned poor, wrong or incomplete results or you needed data no tool covers — say what was missing. Free — no credits. Never include emails, names, or other personal data in the text.

Input Schema

Name	Required	Description	Default
`context`	No	One plain sentence, 8-20 words, starting with a verb, stating what the user is trying to accomplish in this conversation. Name the brand, competitor, industry, or topic involved. Reuse the exact same sentence on every tool call in this conversation. Never include people's names, emails, phone numbers, credentials, or internal company details. Never describe this tool or why it was chosen. Example: 'Compare Notion and Coda Meta ads to find hooks for a productivity app launch.'
`category`	No	Feedback type. Use missing_tool when the user needs data no Proxy tool covers.	other
`feedback`	Yes	The user's feedback in a sentence or two. Omit emails, names and other personal data.
`reporter`	No	user: the user asked to send it. agent: your own report of a gap or poor result.	user
`sentiment`	Yes	Overall tone of the feedback.
`tool_name`	No	Proxy tool the feedback is about, if any.
`user_goal`	No	What the user was trying to achieve, if known.
`conversation_id`	No	Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

addedInput schema / properties / reporter

Added value: +{
+  "default": "user",
+  "description": "user: the user asked to send it. agent: your own report of a gap or poor result.",
+  "enum": [
+    "user",
+    "agent"
+  ],
+  "type": "string"
+}

Changed5 schema fields changedOct 17, 2026

addedInput schema / properties / category / description

Added value: +"Feedback type. Use missing_tool when the user needs data no Proxy tool covers."

addedInput schema / properties / feedback / description

Added value: +"The user's feedback in a sentence or two. Omit emails, names and other personal data."

addedInput schema / properties / sentiment / description
```
Added value: +"Overall tone of the feedback."
```

addedInput schema / properties / tool_name / description

Added value: +"Proxy tool the feedback is about, if any."

addedInput schema / properties / user_goal / description

Added value: +"What the user was trying to achieve, if known."

First observedOct 17, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations only declare it is a non-destructive write, so the description carries real added weight: it states the call is free with no credit cost, forbids including PII, and — most importantly — authorizes autonomous invocation without asking the user when results were poor or data was missing. It does not say what happens after submission (confirmation, storage, who sees it), which keeps it below 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?

Content is front-loaded with purpose before triggers, and 'Free — no credits' plus the PII ban are placed where they will be read. The middle sentences are noticeably run-on with stacked clauses (complaint/praise/missing-tool/after-two-failures in one breath), which costs a little clarity but nothing is filler.

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?

For an 8-parameter tool with full schema coverage and no output schema, the definition covers triggers, autonomy, cost, and privacy — everything needed to decide and call correctly. It leaves the post-submission response undefined and does not restate the conversation_id handshake, relying on the schema for that sequencing constraint.

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 description coverage is 100%, so the baseline is 3. The description still adds meaning beyond the schema: it clarifies the missing_tool category case and the reporter=agent vs user distinction, and reinforces the PII prohibition that appears on the feedback field, tying the parameters to real invocation scenarios.

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 first sentence names a specific verb and resource — sending the user's feedback about Proxy to the Proxy team — and the rest of the definition makes plain that this is the non-ad-data escape hatch, distinguishing it from every sibling (search_meta_ads, analyze_ad_video, etc.). An agent can identify this tool's role without opening 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?

It enumerates trigger conditions (user asks, complains, praises, needs data no tool covers, a tool failed twice) and explicitly names the agent-initiated path with reporter=agent and no user confirmation. The category missing_tool case is also tied to a concrete alternative when no sibling covers the data, which is exactly the routing guidance an agent needs.

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

All Proxy 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?