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

Annotations already establish that this is a safe, read-only, idempotent call, so the bar is lower. The description still adds real behavioral context that the annotations cannot: most lines report no count, so sparse/empty values are expected, and with sort=change lines lacking an old enough sample are pushed to the end. It does not mention rate limits or payload size, but the key data-quality caveat is disclosed.

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?

Three short sentences, front-loaded with what the tool returns rather than with preamble. "For screens and alerts" is slightly clipped and vague, but nothing in the text is redundant.

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 full schema coverage, rich annotations, no output schema and only five parameters, the description only needs to add the delta. It covers the ranking behavior and the important caveat that most lines have no count; what is missing is the distinction from get_line_popularity and any sense of the row shape returned.

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 description coverage is 100%, so sort, limit, league, window_minutes and user_request are all documented in the schema, giving a baseline of 3. The description's phrasing of sort=change ("how fast the count is rising") only restates the schema's "biggest rise over window_minutes" and adds no new detail on window/limit interaction.

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?

"Current lines by reported pick count" states a concrete resource (lines) and ranking basis (pick count), with the alternate ranking mode called out inline. It does not distinguish itself from the close sibling get_line_popularity, which also sounds like it ranks lines by popularity, so an agent must still guess between the two.

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?

"For screens and alerts" gives an implied context but names no alternative tool and no exclusion condition. The two sort modes are effectively a usage guide (use sort=change for rising momentum), but the choice against get_line_popularity or get_line_history is left unaddressed.

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