submit_delegated_job

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 thoroughly. It discloses the pull-after-work model, metered ceiling behavior, delegation cap as max loss, per-session spend limit enforcement, automatic iroh transfer for large inputs, and the no-publish confirmation behavior when max_price_lamports is omitted.

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 description is long but dense, with the main purpose front-loaded and each subsequent sentence adding a distinct behavioral or usage fact. Some redundancy exists around the delegation pulling concept, but it is not excessive given the tool's complexity and risk implications.

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?

The description covers many contextual details—delegation, metering, limits, alternatives, and confirmation behavior. However, it does not state what is returned on a successful submission (e.g., job ID or session ID) and has no output schema to compensate. This is a meaningful gap for an AI agent that needs to interpret the tool result.

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 coverage is only 17%, so the description needed to compensate for undocumented parameters. It adds meaning for input (inline vs iroh), capability (ordinary vs metered), and max_price_lamports, but kind_offset and timeout_secs are never explained. provider_npub is only implied via the delegate key, so the compensation is incomplete.

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 a specific verb ('Submit'), a resource ('a job'), and a distinct payment model ('paid from your existing spl-approve USDC delegation'). It also differentiates from siblings by explicitly naming submit_delegated_job_from_file for file inputs, making the tool's scope clear relative to alternatives.

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?

The description gives explicit when-to-use guidance: use this tool when an active delegation exists and the input is inline. It tells the agent to check get_delegation, states the job will be refused if the session budget is insufficient, and directs file-based jobs to submit_delegated_job_from_file. It also explains the no-max-price confirmation path.

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