Prism by Parad1gm: Contract Deadlines and Critical Dates

Tell the Revalidata team something

prism_send_feedback

Sends a message to the people who build Revalidata and returns a confirmation. Call it when your user corrects a date, deadline or clause Revalidata returned (kind wrong_result, with the contractId and what they say is right); when your user says a document type is not supported or asks for a feature (kind missing); or when your user says what they would pay per contract, or that the price is what stops them (kind price, with wouldPayUsd). Send it only when one of those happened, not after every result. Say what happened in plain words and leave out the contract text and your user's personal details. Free: never spends credits. A person reads every message, but there is no reply to the agent and no promise of a fix, so do not promise your user one. When the team reproduces a wrong result, the account gets 10 free credits.

Input Schema

Name	Required	Description
`kind`	Yes	wrong_result: your user corrects a date, consequence or quote. missing: a document type is not supported, a feature is asked for, or something your user needed is not there. price: the price is the obstacle. other: anything else.
`message`	Yes	What happened, in plain words. Do not paste the contract or your user's personal details.
`contractId`	No	The contract this is about, if any.
`wouldPayUsd`	No	Only if your user said one: what they would pay per contract for Revalidata to be worth it, in US dollars. Do not guess.

Output Schema

Name	Required	Description
`nextStep`	Yes	What the agent should do next, in plain words; null when nothing is needed. A step that would spend credits or money says to ask your user first: do not take it on your own.
`received`	Yes	true once the message is stored.
`feedbackId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 26, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / wouldPayUsd / description

Previous value: -"Only if your user said one: what they would pay per contract for Prism to be worth it, in US dollars. Do not guess."New value: +"Only if your user said one: what they would pay per contract for Revalidata to be worth it, in US dollars. Do not guess."

Changed1 schema field changedOct 1, 2026

changedOutput schema / properties / nextStep / description

Previous value: -"What the agent should do next, in plain words; null when nothing is needed."New value: +"What the agent should do next, in plain words; null when nothing is needed. A step that would spend credits or money says to ask your user first: do not take it on your own."

Changed2 schema fields changedSep 27, 2026

changedInput schema / properties / kind / description

Previous value: -"wrong_result: a date, consequence or quote is wrong. missing: something your user needed is not there. price: the price is the obstacle. other: anything else."New value: +"wrong_result: your user corrects a date, consequence or quote. missing: a document type is not supported, a feature is asked for, or something your user needed is not there. price: the price is the obstacle. other: anything else."

changedInput schema / properties / wouldPayUsd / description

Previous value: -"What your user would pay per contract for Prism to be worth it, in US dollars."New value: +"Only if your user said one: what they would pay per contract for Prism to be worth it, in US dollars. Do not guess."

Changed1 schema field changedSep 17, 2026
- addedInput schema / properties / contractId / minLength
```
Added value: +1
```
First observedSep 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing cost ('Free: never spends credits'), the human-review workflow, the absence of a reply or fix promise, and the 10-credit incentive on reproduction. These are exactly the operational facts an agent needs and none are in the structured fields.

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?

Front-loaded with the action and then the trigger conditions; every clause carries information (cost, privacy, no-reply, incentive). The middle sentence is long and compounded with semicolons, which slightly hurts scanability but wastes no content.

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?

Output schema exists so return values need no explanation, annotations cover safety hints, and the description supplies triggers, exclusions, privacy rules, cost, and follow-up expectations. Nothing an agent needs to call this correctly 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 baseline is 3, but the description adds cross-parameter guidance not present in the schema: which kind pairs with contractId and which with wouldPayUsd. It also reinforces content constraints ('leave out the contract text and your user's personal details') that matter for the message field.

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 ('Sends a message to the people who build Revalidata') plus the return behavior ('returns a confirmation'). This is clearly distinguishable from the sibling tools (buy credits, get/lock contracts, review, deadlines) as the only feedback channel.

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?

Explicitly enumerates the three triggering situations mapped to kinds (wrong_result with contractId, missing, price with wouldPayUsd) and adds a negative condition: 'Send it only when one of those happened, not after every result.' No inference required.

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

All Prism by Parad1gm: Contract Deadlines and Critical Dates 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.