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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to re-litigate safety. It does add genuinely non-obvious behavior: pre-game/inactive-game coverage, exclusion of injured players, and the return payload (last-10 and last-5 counts plus average). The "past results only, not predictions" line usefully prevents the agent from overselling the output.

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 front-loaded with the trigger condition and then layers scope, exclusions, and return shape in short clauses, so every sentence carries information. The one redundancy is enumerating all six leagues in prose when the enum already lists them, which slightly bloats the opening 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?

For a one-parameter, read-only lookup with no output schema, the description covers the trigger, the time window, the population excluded (injured players), the metric definition, and the shape of the return values. An agent has everything needed to call it and to describe results correctly to a user.

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?

There is a single optional parameter with 100% schema coverage, including an enum of six leagues and a description that empty means all sports with games today. The tool description adds no syntax or default nuance beyond that, so the schema is doing essentially all the work here.

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 gives a concrete verb-plus-resource framing: identify which players in today's games have been most consistent lately, operationalized as "reached a stat number in 9 or 10 of their last 10 games." That is specific enough to act on, but it never distinguishes this tool from the sibling get_player_hit_rates, which plausibly answers a very similar question.

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 opens with an explicit trigger ("Use when the user asks which players in today's or tonight's ... games have been the most consistent lately") and scopes usage to games that haven't started yet. What's missing is a negative boundary against get_player_hit_rates, so the agent must guess which of the two to call for a hit-rate question.

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