AstraEye Labs

Start a priced research run

start_research_run

DestructiveIdempotent

Starts the run a quote priced, spending Astra Credits within the member's daily limit. Call it only after the member agreed to that quote's price, and pass the quoteId and the priceCredits they agreed to: a run never starts above it. Returns the run's runGroupId and projectId (follow it with get_research_run). Errors: quote_expired, quote_replaced, price_higher, daily_limit_reached, price_changed, scope_changed, preparing_context, already_started, outcome_unknown.

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": {
      "quoteId": "<quoteId>",
      "priceCredits": "<priceCredits>",
      "clientRequestId": "<clientRequestId>"
    },
    "name": "start_research_run"
  }
}

Input Schema

Name	Required	Description
`quoteId`	Yes	The quoteId from quote_research_run.
`priceCredits`	Yes	The price the member agreed to, as the quote showed it.
`clientRequestId`	Yes	A UUID you generate for this start. Retrying with the same id never starts or charges twice.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 1, 2026

changedInput schema / properties / quoteId / description

Previous value: -"The quoteId from quote_research_run or create_research_project."New value: +"The quoteId from quote_research_run."

AddedNov 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare destructive=true and idempotent=true, but the description goes well beyond: it discloses that credits are charged against a daily member limit, that the run never starts above the agreed price, and it enumerates nine concrete failure modes including the critical outcome_unknown and already_started cases. That is exactly the behavioral context an agent needs before committing spend.

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 the precondition, then returns, then errors. Dense and mostly waste-free, though the nine-item error list is a long tail that could be trimmed to the ones an agent can actually act on.

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?

For a destructive, credit-spending mutation with no output schema, the description covers the gating precondition, the price ceiling, the returned identifiers, the follow-up call, and the failure taxonomy. Nothing material is missing for correct invocation.

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 genuine constraint meaning: priceCredits acts as a ceiling ('a run never starts above it'), tying the parameter to a runtime guarantee rather than just a field label. It does not add anything for clientRequestId beyond what the schema already states about idempotent retries.

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 (starts a run), the precondition resource (a quote that was priced), and the side effect (spending Astra Credits). It also names the follow-up tool (get_research_run) and the return identifiers, making it unambiguously distinct from quote_research_run and list_research_runs.

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?

Gives an explicit gating condition: 'Call it only after the member agreed to that quote's price,' plus what to pass. It also routes the agent forward to get_research_run. Both when-to-call and what-to-do-next are spelled out.

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

All AstraEye Labs 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?