Serialize JSON with sorted object keys for deterministic comparison; not RFC 8785 certification. FREE during validation. No key, credits, wallet or preparation needed. Supply your task in input. Existing source and input limits apply.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| profile | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / maxPriceMicroUsdRemoved value: -{
- "description": "Optional legacy field; ignored in free mode.",
- "minimum": 0,
- "type": "integer"
-}Input schema / properties / requestIdRemoved value: -{
- "description": "Optional legacy field; ignored in free mode.",
- "type": "string"
-}Input schema / properties / maxPriceMicroUsd / descriptionPrevious value: -"Explicit maximum new debit; 0 means recovery only."New value: +"Optional legacy field; ignored in free mode."Input schema / properties / maxPriceMicroUsd / maximumRemoved value: -999999999999Input schema / properties / requestId / descriptionPrevious value: -"Persist the ID returned by agent_utilities_prepare. Reuse after uncertainty."New value: +"Optional legacy field; ignored in free mode."Input schema / properties / requestId / patternRemoved value: -"^\\d{13}_[A-Za-z0-9_-]{16,80}$"Input schema / requiredPrevious value: -[
- "input",
- "requestId",
- "maxPriceMicroUsd"
-]New value: +[
+ "input"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only/non-destructive, but the description adds genuinely new context: no key, credits, wallet or preparation required, free during validation, and that existing source/input limits apply. The only tension is idempotentHint=false against a tool described as deterministic, though that is an annotation oddity rather than a description that misleads about what the tool does.
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?
The purpose and the RFC 8785 caveat are correctly front-loaded, but the middle sentences ('FREE during validation. No key, credits, wallet or preparation needed.') are vendor boilerplate, and 'Supply your task in input' consumes space without adding meaning.
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?
Return values are covered by the output schema and safety by annotations, so the description needn't repeat them. Still missing for a single-param, nested-input tool: what the payload should contain and how it relates to the sibling JSON tools an agent would pair it with (diff, patch, pointer).
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 0% and the single parameter is a nested object whose 'data' property is entirely untyped and undocumented. The description's only guidance is 'Supply your task in input', which is confusing filler that points at the wrapper rather than explaining that input.data carries the JSON document to be canonicalized.
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+resource+effect: 'Serialize JSON with sorted object keys for deterministic comparison', and explicitly bounds it with 'not RFC 8785 certification'. An agent can tell this apart from data_json_diff or data_json_patch in intent, but the description never names or contrasts those siblings, which is what a 5 would require.
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?
'for deterministic comparison' implies the use case, and 'not RFC 8785 certification' implies when this is insufficient. However there is no explicit when-to-use/when-not or routing to alternatives such as data_json_diff, so usage is only inferred rather than stated.
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.