Screen for AI

Get operation status

operation_get

Read-onlyIdempotent

Returns the current stage, terminal result, and redacted error of an authorized operation. A slow phone can take a minute or more to apply a page. With wait_seconds (1-10), operation_get answers once the operation is final (applied, failed, expired or superseded) or when that time is up, whichever comes first, with the stage at that moment; without it, at once. A slow phone can need several such calls. Screens on the hosted relay route answer at once either way.

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": {
      "operation_id": "<operation_id>"
    },
    "name": "operation_get"
  }
}

Input Schema

Name	Required	Description	Default
`operation_id`	Yes
`wait_seconds`	No	Seconds (1-10) the call may wait for the operation to become final; 0 or absent answers at once. An operation that is not final yet can still become final until its expires_at, and a later call reports its stage then.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0

Behavior4/5

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

Beyond the readOnly/idempotent annotations, it discloses that errors are redacted, that wait returns the stage at the moment of timeout rather than erroring, and that relay-routed screens answer at once regardless. Minor blemish: it says 'wait_seconds (1-10)' while the schema permits 0, and the final sentence ('answer at once either way') is ambiguous about which behavior applies.

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?

Front-loaded with the return content, which is good, but there is redundant repetition ('A slow phone can take a minute or more to apply a page' and 'A slow phone can need several such calls') and the range '1-10' duplicates the schema while contradicting it on 0.

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?

An output schema exists, so return-shape explanation is not required, yet the description still names the returned fields helpfully. For a two-parameter read tool the coverage is nearly sufficient; the remaining gap is where an operation_id comes from and what 'superseded' implies operationally.

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

Parameters3/5

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

Schema description coverage is 50%; wait_seconds is already well documented in the schema, and the description largely restates its blocking semantics while adding the useful point that non-final operations remain finalizable until expires_at. operation_id is undocumented in both schema and description (no format, no source of the ID), so the description does not compensate for the coverage gap.

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 ('Returns the current stage, terminal result, and redacted error of an authorized operation') and enumerates the terminal outcomes (applied, failed, expired, superseded). This is clearly distinct from the sibling device/display/page tools, which deal with devices and content rather than operation lifecycle.

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?

Explains the core usage decision: pass wait_seconds to block until final or timeout, omit it to answer immediately, and that 'a slow phone can need several such calls' (i.e., repeated polling is expected). It does not explicitly name an alternative tool or state when not to use this one, but the wait/no-wait guidance is concrete.

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

All Screen for AI 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?