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

The description goes far beyond the readOnly/idempotent annotations. It carefully distinguishes held_to_end as a MEASUREMENT vs clock_upper_bound as a CEILING, explains rugged launches are counted as zero, notes launches without a recorded multiple are excluded from both stake and return, and flags the Robinhood data limitation. It also warns how to quote the ceiling ('Say at most'), which is genuinely useful behavioral guidance.

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 dense and long, but nearly every sentence earns its place by adding a semantic caveat or scope limitation. It front-loads the core purpose and output shape before diving into measurement/ceiling distinctions. It could be broken into clearer bullets, but it is not padded or redundant.

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 carries the burden of explaining return semantics, and it does so thoroughly for held_to_end and clock_upper_bound. It also covers exclusions and platform limitations. Minor gaps remain: 'band p25' is not defined, and computed_for/of are referenced without explaining what they contain, so an agent may still be slightly uncertain about the exact output row fields.

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 defines n, usd, and creator with defaults and types. The description contextualizes these parameters inside the $100 and 'last N resolved launches' scenario but adds no new parameter-level constraints or format details beyond the schema. The 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?

The description opens with a concrete scenario: 'What $100 would have done across a creator's last N resolved launches.' It also states the output shape ('Returns two rows'), so an agent can tell this is a historical replay/backtest tool. It does not name a sibling alternative or explicitly distinguish itself from tools like groundtruth_scorecard, so it stops short of a 5.

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 implies usage: call this when you need a historical '$100 stake' replay across a creator's resolved launches)Skip it for unsupported platforms. It gives a platform constraint ('Solana only today') but never states when to prefer this over siblings or when not to use it. The usage context is mostly implied rather than explicit.

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