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

Annotations already carry readOnly/idempotent/destructive safety, so the description earns credit for adding 'no auth' and the privacy guarantee that individual bidder identities are never revealed. It also discloses output shape (row fields and sort order), which is not in the schema. No contradiction with 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?

Two compact sentences front-load the purpose and sort order, then enumerate output fields and constraints. No filler.

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 simple, one-parameter read-only tool with no output schema, the description covers scope, ordering, row fields, auth, and privacy. The only minor omission is stating 'returns a list' explicitly, but this is strongly implied by 'leaderboard' and 'each row.'

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?

The single parameter (limit) is fully documented in the schema (default 20, max 100), so the description carries no burden here. It doesn't add any usage nuance about the parameter, so 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 identifies the resource ('open features') and the exact output contract: ranking order ('most ET10 bid first, then votes') and per-row fields. It distinguishes itself from sibling tools like feature_bids/feature_my_bids by explicitly saying 'Never who bid what.' It lacks an imperative verb like 'lists', but the behavior is unmistakable.

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 'open features' scope plus 'Never who bid what' gives an agent clear context for when the leaderboard is appropriate and when a per-account bid detail tool would be needed. It doesn't name the alternative tools explicitly, so the routing instruction is implicit rather than explicit.

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