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

With no annotations, the description carries the full burden and excels. It discloses all return blocks (prediction, conformal_interval, voter_decomposition, context), edge cases (ticker not in universe returns available:false with reason), caching (5min), namespace (US-EQUITY only), and the crypto collision behavior with exact ticker names. This is exemplary behavioral disclosure.

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 every sentence provides unique value: return structure, refresh cadence, universe size, cache, namespace, collision list, and usage warning. It is well-organized with clear blocks and no repetition. Complex tool, appropriately detailed.

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 complexity (multiple named return blocks, edge cases, no output schema), the description is complete. It covers the prediction, interval, voter decomposition, context fields, unavailable scenario, cache, US-equity scope, crypto collision handling, and the fail-closed 404. No critical information is missing for an agent to select and invoke the tool correctly.

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 50% (ticker has a generic description, asset_class has none). The description compensates fully: it explains asset_class is an enum with default equity, defines the crypto collision scenario, and clarifies that ticker refers to US-equity tickers within the namespace. This adds critical meaning beyond the schema.

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 the tool's purpose: 'Latest ensemble ML prediction for the ticker, with full conformal interval + 19-voter decomposition.' It specifies the resource (ticker) and the exact output structure, distinguishing it from related sibling tools like tengu_ml_predict or tengu_v3_intel_ml_drivers by emphasizing the conformal interval and voter decomposition.

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 clear context for when to use: it's the US-equity prediction tool, refreshed nightly, and explicitly warns against using it for crypto (with asset_class handling and failure mode). However, it does not explicitly name alternative tools or contrast with tengu_ml_predict, so it stops short of full when/when-not alternatives guidance.

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