submit_and_pay_job_from_file

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

With no annotations provided, the description carries full burden. It discloses the file transfer mechanism (peer-to-peer via iroh), how input reaches the skill (stdin or env var), and security constraints (allow_outside_cwd restricts file access, sensitive files always refused). It does not cover error handling or what happens if the file is missing, but overall provides good behavioral insight.

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 a single paragraph that packs essential information without fluff. It front-loads the relationship to the sibling tool. However, it could be more structured (e.g., bullet points for prerequisites) to improve skimmability. On balance, it is concise for the amount of detail.

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?

Given the tool complexity (7 parameters, no annotations, no output schema) and the presence of a similar sibling, the description covers when to use, how transfer works, prerequisites, and key parameter semantics. It lacks examples of input_path usage or error scenarios, but the essential contextual information is present.

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 low (29%), so description must compensate. It adds meaning to input_path (absolute or relative to working directory) and explains the security semantics of allow_outside_cwd. It also clarifies that file content never enters LLM output tokens, giving context to the parameters. However, parameters like provider_npub, capability, timeout_secs receive no extra explanation beyond their names.

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 clearly states it is the same as submit_and_pay_job but reads input from a file, distinguishing it from its sibling. The verb 'read' and resource 'file' are explicit, and the comparison to the sibling tool provides immediate context.

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 explicitly tells when to use this tool: 'when the input is large or binary (images, logs, captured output)'. It also lists prerequisites: 'persistent agent, a PAID provider skill, and the iroh addon'. No when-not-to-use is stated, but the positive guidance is strong and clear.

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