submit_task

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

With no annotations, the description carries the full burden and does so well: default read-only, isolated clean Git worktrees for code jobs, bounded 30-minute attempts for heavy profiles, automatic bounded provider fallback with no paid API fallback, and it explicitly says the prompt is never echoed. Missing only permission/auth and mutation side-effects for create_workflow.

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

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

The purpose is front-loaded, but the body is a dense semicolon-joined run-on mixing purpose, safety, fallback, and return behavior. It is terse yet unstructured, and the external doc reference ('See the DeltaRoute heavy-workflows reference') adds noise.

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

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-param tool with nested objects, an anyOf of three call shapes, and no output schema, the description is only partially complete. It helpfully states the return shape ('compact status/result and full artifact path'), but does not explain the anyOf call patterns, the limit_error reporting flow, or permissions.

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

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

Schema description coverage is only 28% across 18 params, so the description must compensate but largely does not. It mostly repeats enum values already in the schema (action names, mode) and the wait_seconds bound, adding only 'default read-only' for mode; key params like category, provider, detail, context, research_scope, and media_options get no elaboration.

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

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

The description states specific verbs and resources ('Delegate a task or manage a heavy workflow') and enumerates the workflow actions (create_workflow, run_step, checkpoint). It is clearly distinguishable from siblings like get_task and cancel_task, though it never names them explicitly to route the agent.

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

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

It implies usage contexts (heavy workflows, short jobs via wait_seconds, code jobs) and points to a 'DeltaRoute heavy-workflows reference,' but gives no explicit when-to-use vs when-not guidance relative to recommend_route or get_task. Usage must be inferred.

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