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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond that: it specifies the ranking order, describes the exact fields returned (rank, wallet_address, total_score, components, etc.), mentions the pre-token disclaimer, and notes the limit cap. This is useful context that assists an agent in understanding the tool's behavior without redundancy.

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 two sentences plus a parenthetical, extremely concise and highly informative. The key facts are front-loaded: 'Top-N Crank Score leaderboard (FREE read)' immediately gives the purpose and cost. Every sentence adds new information: ranking, fields, disclaimer, and the sibling distinction. No filler words or redundancy.

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 that an output schema exists (has output schema: true), the description doesn't need to repeat return types, but it still lists all the fields that will be included, which is helpful. It explains the limit cap, the ordering, and the distinction from the sibling. The only minor gap is the `caller_id` parameter, but since the tool has no required parameters and is a read operation, the description is essentially complete for an agent to call it 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 coverage is 0%, so the description must fully explain parameters. It does explain `limit` clearly: it caps at the admin-configured leaderboard_size, which adds meaning beyond the schema's bare type. However, it entirely omits `caller_id`, leaving that parameter's purpose and usage unexplained. Since one of two parameters is undocumented, the description only partially compensates for the lack of schema coverage, so a 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 states a specific verb and resource: 'Top-N Crank Score leaderboard'. It clearly identifies what is being retrieved (leaderboard of Crank Scores) and the key ordering (descending by total_score). It also distinguishes itself from get_leaderboard, which ranks strategy templates, so an agent can immediately recognize this tool's unique purpose.

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 gives explicit guidance: it says it's a FREE read, meaning no cost or side effects. It also states that `limit` caps at the admin-configured leaderboard_size, setting expectations for the parameter's behavior. Most importantly, it explicitly differentiates from get_leaderboard, telling the agent when NOT to use this tool (for strategy templates). This is explicit when/when-not guidance.

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