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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description adds real value beyond them by disclosing the POLYRANK_API_KEY auth requirement and by describing what the payload contains (raw value plus cohort percentile per window) even though there is no output schema. It also explains scope=combined reads the multi-wallet user row 'as boards do', which is behavior not inferable from 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?

Purpose is front-loaded in the first clause, then the window list, then the identifier/scope/auth details — a sensible ordering with no filler sentences. The phrasing is dense to the point of being cryptic in places ('the cells a board ranked at that window scores'), which costs a point.

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 4-parameter read tool with no output schema, the definition covers the essentials: what is returned (value + percentile), the window dimension, identifier options, scope default, and the API-key requirement. Minor gaps remain — precedence if both tid and address are supplied, and behavior when a trader has no data in a window — but nothing critical 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?

Schema coverage is 75%, so baseline is 3; the description goes beyond it by giving semantics for the undescribed 'scope' parameter (combined = multi-wallet user row, the default) and by clarifying that tid is a masked board identifier while address is a proxy wallet — effectively an either/or rather than both-required. Window values and the tid/address formats are repeated from the schema, so no extra credit there.

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 resource and verb implicitly: 'One trader's every metric ... the raw value and its percentile in that window's cohort' — an agent knows it returns a full per-trader metric set, not a ranking. It implicitly separates itself from narrower siblings (get_trader_skill, get_trader_calibration) by being the comprehensive metric read, but it never names them, so sibling differentiation is left to the agent.

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 calling guidance — 'Give a wallet address or a masked tid' resolves the otherwise ambiguous zero-required-parameter schema, and it states scope=combined is the default. But there is no explicit when-to-use/when-not-to-use versus alternatives (e.g., get_trader_by_tid, get_traders_batch, rank_wallets), so usage is implied rather than stated.

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