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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description does not need to restate those. It adds valuable nuances: rates are only claimed when enough clean samples exist, otherwise only rows are listed, results are the same on every plan, and it is descriptive market data only. These details go beyond the structured annotations and meaningfully shape 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 information-dense with no filler. Each sentence adds a necessary aspect: output contents, use-case examples, sample-threshold behavior, plan consistency, differentiation from the sibling tool, and data nature. It is front-loaded with the core function.

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 a read-only query tool with an output schema and rich annotations, the description covers purpose, usage context, edge-case behavior (insufficient clean samples), plan consistency, and sibling distinction. Nothing an agent needs to correctly select and invoke this tool is missing.

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?

Input schema covers 100% of parameters with descriptions, including allowed signal types, coin examples, and limit bounds. The description adds context about 'last N firings' which maps to the limit parameter, but does not need to compensate for any schema gaps. Baseline 3 is appropriate given full schema coverage.

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 specific operation: showing how the last N firings of one signal type on one coin played out over 24h, with counts, median move, and underlying rows. It explicitly differentiates from flag_outcomes as the market-wide ledger, so an agent can distinguish it from a sibling with no ambiguity.

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 concrete example queries ('how have funding-extreme flags on ETH worked out') and explicitly contrasts with flag_outcomes ('this is one type on one coin'). This gives clear when-to-use and when-not-to-use guidance without needing to infer from parameter names.

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