Contract Lily

Start a contract review

start_contract_review

Send a whole UK tenancy agreement or employment document to Contract Lily for a full review, with the user's agreement to send it. Pass the attached file, or else the document's complete text, word for word; a summary or excerpt gives a wrong review. It returns a reviewId for get_contract_review. The review reads the document against UK law and returns a verdict, findings and a PDF report. Results are recommendations, not legal advice.

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": {
      "family": "<family>"
    },
    "name": "start_contract_review"
  }
}

Input Schema

Name	Required	Description
`file`	No
`text`	No	The document's complete text, word for word with its clause numbers, when no file can be passed. Never a summary or an excerpt.
`family`	Yes	The kind of contract: a home tenancy, or an employment document.

Output Schema

Name	Required	Description	Default
`pdfUrl`	No
`reason`	No
`status`	Yes
`verdict`	No
`findings`	No
`reviewId`	Yes
`questions`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations (which already flag a non-read-only, open-world, non-idempotent write), it discloses the consent requirement, the review basis (UK law), and what comes back: a verdict, findings and a PDF report, plus the disclaimer that results are recommendations, not legal advice. It does not say what happens on a duplicate submission, which matters given idempotentHint=false.

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?

Four tight sentences, front-loaded with the action and scope; the consent requirement and the completeness warning each sit next to the input they govern. No sentence 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?

With an output schema handling return values and annotations covering the safety profile, the description carries only what those cannot: consent, exact input fidelity, and the reviewId handoff to get_contract_review. The only remaining gap is repeat-call behavior for a tool marked non-idempotent.

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 67%, and the description compensates for the gap: it spells out that file and text are alternatives, and that text must be the complete word-for-word document because a summary or excerpt yields a wrong review. It reinforces the family parameter by naming the two contract kinds, though it does not mention the 262144-character limit.

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?

Names a specific verb (start) and resource (contract review) and scopes it to whole UK tenancy agreements or employment documents sent to Contract Lily. That scope distinguishes it from the sibling check_* tools, which test single clauses or statutes rather than reviewing a full document.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

States the precondition (the user must agree to send the document) and the file-vs-text fallback, and points to get_contract_review as the follow-up that consumes the returned reviewId. It never says when not to use it, e.g. how to handle a document already under review or one outside the two supported families.

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

All Contract Lily 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?