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

Annotations cover only the safety profile (read-only, idempotent, open-world); the description carries all the substantive behavior: it defines the two returned rows, states held_to_end counts rugged launches as zero, explains that clock_upper_bound is a ceiling derived from the peak rather than a prediction, and discloses that launches lacking a recorded multiple are dropped from both stake and return.

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?

Front-loaded with the core purpose, then proceeds through the caveats in a logical order. It is dense and long, but for a measurement tool with no output schema nearly every sentence (ceiling vs measurement, exclusion rule, chain limit) earns its place; only mild redundancy holds it below 5.

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?

With no output schema, the description fully discharges the burden of explaining return values (two named rows with their exact semantics), the exclusion rule that keeps both rows over the same set, quoting guidance, and the Solana-only limitation. An agent has what it needs to call and interpret it.

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 n, usd, and creator are already documented with types and defaults; the description adds only contextual framing ('last N resolved launches') and references output fields (computed_for, of) rather than enriching parameter meaning. Baseline 3 is appropriate.

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?

States a specific verb+resource: it replays what a $100 stake would have returned across a creator's last N resolved launches. An agent can tell this apart from screening/scanning siblings because it is explicitly a retrospective per-creator replay, though it never names an alternative sibling to route away from.

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?

Usage is implied by the framing (evaluating a creator's historical launch performance) and constrained by the Solana-only caveat, but there is no explicit 'use this when / not when' guidance or reference to sibling tools that might be the better choice.

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