ProofSnap

Export a matter as one ZIP

export_matter

Builds one ZIP of a matter for the owner of the matter (a Legal plan, or Archive only for matters kept from one): the custody report, the custody log and the evidence package of each capture, with Bates-numbered filing copies. Returns a download link valid for 15 minutes. A large matter is built in the background: call again with the returned job_id to get the link. Each export counts toward a daily limit of 50.

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": {
      "matter_id": "<matter_id>"
    },
    "name": "export_matter"
  }
}

Input Schema

Name	Required	Description	Default
`job_id`	No	Only to check a background export started earlier.
`matter_id`	Yes	The matter, for example mat_...

Output Schema

Name	Required	Description
`job_id`	No
`status`	No	ready, processing or failed
`matter_id`	No
`expires_at`	No
`size_bytes`	No
`bates_prefix`	No
`generated_at`	No
`capture_count`	No
`custody_events`	No
`exhibits_count`	No
`captures_skipped`	No
`captures_included`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses the 15-minute download link lifetime, the background-job pattern for large matters, and a hard quota of 50 exports per day. Together with the non-idempotent annotation, the agent knows repeated calls consume quota.

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?

Three sentences, front-loaded with what the export produces, followed by the return/follow-up behavior and the quota. No filler or redundancy.

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?

With an output schema present, the description needn't detail return values, and it still covers the async flow, link expiry, and rate limit. Nothing essential for a correct invocation 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 meaning the schema lacks: job_id is used only to re-check a background export started earlier, and matter_id is tied to the contents being exported. This clarifies the two-mode calling pattern.

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 (builds one ZIP of a matter) and enumerates the contents: custody report, custody log, per-capture evidence packages with Bates-numbered filing copies. No sibling tool exports anything, and the scope is unambiguous from the first clause.

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?

Specifies eligibility (owner of the matter, Legal plan, or Archive-only for retained matters) and the follow-up call with the returned job_id for large matters. It does not name an alternative tool or explicitly say when not to use it, but no sibling provides a comparable capability.

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

All ProofSnap 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.