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

While annotations indicate readOnlyHint=false and other flags, the description goes far beyond them by disclosing the flat sats payment contingent on passing a Monte-Carlo permutation p-value and Deflated Sharpe gate, the three-tier auto-detection, and the hardened network-off Docker sandbox for code-tier. It also specifies the required generate_signals(candles) function. This is rich behavioral context not available in the annotations.

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 three sentences, each earning its place: purpose, payment/gate, tier definitions. It is front-loaded with the core action and avoids redundancy with the schema. The structure is logical and no words are wasted.

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's complexity (nested spec, multiple tiers, no output schema), the description provides essential operational context: the evaluation gate, the payment, the tier detection, and the code sandbox. Even without an output schema, it tells the caller what to expect in terms of outcomes (payment if the idea survives), making it sufficiently complete for correct invocation.

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 100%, so the schema already documents each parameter. The description adds meaningful semantics to the 'spec' parameter by explicitly stating that code-tier signal_code must define generate_signals(candles), a detail not present in the schema. This extra guidance compensates for the otherwise terse object description, though the schema already covers the three tier shapes.

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 a clear verb and resource: 'Submit a trading-edge idea to the governed edge-idea bounty.' It differentiates from siblings by explaining the flat sats payment and the three auto-detected tiers, making it unmistakably the tool for submitting an edge idea rather than generic feedback or a ledger entry.

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 clearly implies when to use the tool (when you have a trading-edge idea to submit) and explains the tier structure, which guides the user on what 'spec' should contain. However, it does not explicitly state when not to use it or mention alternatives such as bounty_get for checking status, preventing a perfect score.

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