ProofSnap

Refresh a capture card

poll_capture

Read-onlyIdempotent

Returns the current state of a capture for the capture card; with download true, a 15-minute download link of the evidence package for the card's Download button.

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": {
      "capture_id": "<capture_id>"
    },
    "name": "poll_capture"
  }
}

Input Schema

Name	Required	Description	Default
`download`	No	Issue a 15-minute download link of the evidence package for the card's Download button. Default false.
`capture_id`	Yes

Output Schema

Name	Required	Description	Default
`status`	No
`capture_id`	No
`captured_at`	No
`manifest_hash`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

removedInput schema / properties / verify

Removed value: -{
-  "description": "Verify the stored evidence package, as verify_capture does, for the card's Verify button where the host answers only this tool. Default false.",
-  "type": "boolean"
-}

Changed1 schema field changedNov 4, 2026

addedInput schema / properties / verify

Added value: +{
+  "description": "Verify the stored evidence package, as verify_capture does, for the card's Verify button where the host answers only this tool. Default false.",
+  "type": "boolean"
+}

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / download / description

Added value: +"Issue a 15-minute download link of the evidence package for the card's Download button. Default false."

First observedOct 31, 2026

TDQS

B3.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the download link is time-limited to 15 minutes and is tied to a card's Download button. It doesn't say whether successive download calls mint new links, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, but it is clunky, repeating 'for the capture card'/'for the card's Download button' and using an awkward semicolon splice. The most important statement (returning capture state) is front-loaded, but the sentence could be tightened considerably.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

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 needn't be spelled out, and the annotations cover safety. What's missing is the required capture_id's provenance and how this tool differs from get_capture, both of which an agent needs to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: the download flag is already documented in the schema, and the description largely restates that same wording with no added meaning. capture_id — the only required parameter — is undocumented in both schema and description, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Returns the current state of a capture.' The framing 'for the capture card' signals a UI-refresh use case. However, it never contrasts itself with the sibling get_capture, which the agent must choose between, so it falls short of full sibling differentiation.

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

Usage Guidelines3/5

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

The description explains the download=true branch (fetch a Download-button link) but gives no guidance on when to poll versus calling get_capture, or how often polling is appropriate. Usage is implied by the scenario, not stated.

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.