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

Annotations already declare read-only, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description goes further by disclosing output limitations ('no price, no size of the fall and no multiples'), the exact unit convention for discounts (-84.47 means −84.47 %), and a non-recommendation disclaimer. It does not discuss staleness/refresh of the snapshot or rate limits, but for a read-only snapshot the added context is substantial.

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 primary purpose is front-loaded in sentence one and every later sentence carries information (use cases, units, output caveats, disclaimer). It is dense and slightly long, especially the enumerated timeframes, but there is no filler sentence.

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 an output schema present, return values need not be re-explained, yet the description still warns about what the answer lacks and how to interpret discounts, which covers the tool's main trap. Details such as the meaning of 'changes in the line-up' and how the selection rules are conveyed remain inferential, but nothing needed to invoke it correctly 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 100% so the baseline is 3, but the description adds meaning beyond the schema by explaining what each ranking_id value is for and by defining the unit of the discount values returned. The lang parameter's effect on names is left to the schema, which is acceptable at full coverage.

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 opening sentence states a specific verb and resource ('The latest snapshot of ONE ranking') and enumerates the payload (place, ticker, name, sector, changes in line-up, selection rules). The word 'ONE' plus the contrast with screener clearly separates it from list_rankings and screener. An agent can identify the tool without opening the schema.

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?

It gives explicit use cases mapped to ranking_id values: 'which stocks are undervalued' → undervalued_relative, and 'which fell the most over a day / week / month / three months / year' → the fallen_* variants. It also routes the agent elsewhere for valuation multiples ('multiples come from screener'), which is a genuine when-not-this-tool signal.

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