create_contract_b

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

With no annotations, the description fully carries the burden and excels. It discloses key behaviors: locks payment from wallet, worker must commit collateral, timeout review allows worker claim, expiry_block causes collateral forfeiture if no delivery, dispute_fee is non-refundable, and returns confirmation/error. These details go far beyond minimal expectations.

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 relatively long but every sentence is value-dense. It is well-structured: main purpose, lifecycle, usage guidance, then parameter list. Front-loaded with the core action and decision-relevant information. No fluff or repetition.

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 11-parameter tool with no output schema given, the description is remarkably complete. It covers the entire contract lifecycle, timeout behavior, collateral forfeiture, dispute handling, and return values. It also ties into sibling tools (commit_collateral, claim_after_timeout) and gives practical block-height estimates.

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 0%, so the description must compensate, and it does comprehensively. Every parameter is explained with units, valid values, defaults, and purpose: payment in groth, asset_id 0/47, expiry_block estimated in days, review_window_blocks conversion, dispute_fee implications, required_collateral floor, optional spec_hash. This is exemplary parameter documentation.

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 opens with 'Create a Mode B (Reviewed settlement) Idios escrow contract' – a specific verb (create) plus resource (Mode B escrow contract). It clearly distinguishes from siblings by detailing the review workflow and explicitly recommending Mode B for work requiring human/agent judgment, unlike other contract types.

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?

Provides explicit use case: 'Use Mode B for any work where a human or agent needs to judge the output: custom AI agents, automation pipelines, consulting, data labelling, model fine-tuning where exact output hash is not known in advance.' This implies when not to use (e.g., when output hash is known, likely Mode A). It also outlines the complete workflow and prerequisites (worker must call commit_collateral).

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