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

Annotations already declare readOnlyHint=true, openWorldHint=false, and destructiveHint=false, establishing the safe-read profile, so the description need not re-state safety. It adds useful provenance and scope (data windows of ~72 cuts/126 trading days, source mirror closelook.net/stocks/rankings/), but discloses no operational behavior such as freshness, caching, or rate limits. Modest added value over 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?

It is a dense, front-loaded paragraph: the tool's identity and relationship to get_df_ranking lead, followed by the family breakdown. Nearly every clause carries information (universe sizes, view options, data source). It is crowded but not padded; sentence structure is efficient given the breadth of families covered.

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?

There is no output schema, so the description carries the return-format burden, yet it never describes the shape of the result (columns, metrics per row) beyond the qualitative 'ranked' framing. Given three families with distinct metrics, an agent would benefit from knowing the return structure. Adequate for choosing the tool, incomplete for interpreting output.

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 baseline is 3, but the description goes further by explaining what each family actually measures and mapping which views (top/momentum, leaders/fragile/unstable, divided/today/broadest) belong to which family. This semantic detail helps an agent choose family/view combinations beyond the bare enum values.

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 resource (Closelooknet ranking families) and enumerates each family with its underlying universe (US-listed ETFs, ~2,700 stocks, 40 funds) and dimensions, so an agent knows exactly what data is returned. It explicitly positions itself as the sibling of get_df_ranking (end-of-day), which aids discrimination. It stops short of a crisp verb-first sentence like 'returns ranked lists,' but the resource and scope are unambiguous.

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?

Labeling these as the 'other daily ranking families (siblings of get_df_ranking, end-of-day)' gives implicit routing context, and the per-family view names hint at when each cut applies. However, there is no explicit when-to-use/when-not or a stated condition distinguishing this tool from get_df_ranking or other ranking-style siblings. Usage is implied rather than spelled out.

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