submit_feedbackSend feedback to the ManyLives operator: bugs, ideas, praise, complaints, questions. No account needed.
| Name | Required | Description | Default |
|---|---|---|---|
| rating | No | Optional: how you rate ManyLives, 1 (poor) to 5 (great). | |
| context | No | Optional: anything that helps us reproduce it (task id, tool, request). | |
| message | Yes | Your feedback, in plain words. | |
| category | No | What kind of feedback it is. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "type": "object"
+}Input schema / properties / category / descriptionAdded value: +"What kind of feedback it is."Input schema / properties / context / descriptionAdded value: +"Optional: anything that helps us reproduce it (task id, tool, request)."Input schema / properties / message / descriptionAdded value: +"Your feedback, in plain words."Input schema / properties / rating / descriptionAdded value: +"Optional: how you rate ManyLives, 1 (poor) to 5 (great)."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=false already signals this is a write/mutation, so the annotation carries the safety profile. The description adds a genuine auth detail ('No account needed'), which is helpful behavioral context, but it says nothing about rate limits, what happens after submission, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences with zero filler; the core purpose and the acceptance scope are stated immediately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
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 explained, and all four parameters are fully documented in the schema. The description covers purpose, accepted categories, and the no-account requirement, leaving only the sibling distinction unaddressed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and each parameter (rating, context, message, category) is already documented in the schema, so the description need not carry param detail. The enumerated feedback types loosely mirror the category enum but add no syntax or format meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Send feedback') and resource ('to the ManyLives operator'), and enumerates the kinds of feedback accepted (bugs, ideas, praise, complaints, questions) which map directly to the category enum. It is clearly distinct from submit_review/submit_statement, though it never names those siblings explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it (whenever you have feedback for the operator) and adds a useful condition ('No account needed'), but it never states when to prefer it over siblings like submit_review or submit_statement. Usage is inferable rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.