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

Annotations already declare readOnly/idempotent/non-destructive/no-open-world, so safety is covered; the description adds real value beyond that by stating it is free with no key and that entry-timing ids are 'lifetime-pinned' and that as_of refusals come with a stated reason. It stops short of saying whether the payload is a static reference table or computed per request.

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 window enumeration and the as_of clause are front-loaded and no sentence is filler; 'Free, no key' is a useful trailing qualifier. The middle sentence is dense with stacked parentheses and semicolon-free lists, which costs a little readability for an otherwise tight definition.

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 parameters, no output schema, and annotations covering the safety profile, the description carries the remaining burden and does so: it enumerates windows, capability flags, pinned id categories, and explicitly lists what as_of answers plus that refusals are explained. Missing only a note on response shape or how to interpret the refused-filter reasons.

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?

Zero parameters, so per the rubric the baseline is 4, but the description spends several clauses describing output content ('its metrics, the filters it honours and the reason for each it refuses') that reads as parameter-like scoping language without any actual input to govern. With no output schema present, that content is better credited under completeness than here, so a small deduction applies.

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 names the exact resource (metric-to-window availability across lifetime/90d/30d/7d/24h) plus weighting/gating/filtering capability and as_of coverage, so an agent knows what the tool returns. However, it never distinguishes itself from the very similar sibling polyrank_get_metrics_catalog, which the agent could reasonably confuse it with.

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 line 'The reference for ranking at a window or as_of' implies when to reach for it — before constructing a ranked query — and 'Free, no key' lowers the cost of calling it. But there is no explicit when-not, no named alternative (metrics_catalog, lab_limits), and no statement of whether it must be called before rank_wallets or get_custom_ranking.

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