Agents-Core

Overview Schema Source Related Servers Discussions Admin

Submit local generation

local_generate

Submit a bounded textual completion and return a job ID to poll for results; this tool never executes output or spawns agents.

Instructions

Submit one bounded textual completion and promptly return its job ID.

Poll local_generation_result; this tool never executes output or spawns agents.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	Integer seed 0..2147483647, default 42.
`task`	Yes	Required nonempty UTF-8 task, at most 64 KiB and owner limit. JSON-looking text remains exact text.
`cache_mode`	No	auto(default) or off. off disables native reuse and snapshot I/O.	auto
`context_id`	Yes	Required context ID.
`request_id`	Yes	Required canonical lowercase UUID idempotency key. Same ID/grant/arguments returns the original job.
`temperature`	No	Finite sampling temperature 0..2, default 0.
`access_token`	Yes	Required scoped access capability; keep outside task text and logs.
`timeout_seconds`	No	Total job deadline 1..600 seconds, default 120, capped by owner/context/grant expiry.
`max_output_tokens`	No	Output allowance 1..2048, default 512, capped by owner/context/grant and effective model context.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv26.10.16Oct 16, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already establish the safety profile (readOnly=false, destructive=false, openWorld=false). The description adds genuine value beyond them by declaring the asynchronous contract ('promptly return its job ID') and the no-side-effect boundary ('never executes output or spawns agents'). It omits idempotency-by-request_id behavior and cancellation, but the annotations mean the bar is lower.

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?

Two short, front-loaded sentences with zero filler. The core action is stated first, followed by the follow-up step and the scope boundary.

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 present, return values need no explanation, and the description correctly focuses on the async pattern and the no-execution boundary. Minor gaps remain: it doesn't mention the cancel tool or that job deadlines are capped by grant expiry, though the schema covers timeouts.

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 100% across all 9 parameters, so the schema fully documents seed, task, cache_mode, request_id, timeout, and token limits. The description adds no parameter-level detail beyond that, so the baseline of 3 is appropriate.

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 - 'Submit one bounded textual completion' - and clarifies the return contract ('promptly return its job ID'). This clearly distinguishes it from local_generation_result, which is the polling counterpart.

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?

Explicitly routes the agent to the next step ('Poll local_generation_result'), giving clear usage context. It does not, however, state conditions for when-not to use this tool or mention local_generation_cancel as an alternative path.

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

Deploy Server