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

Annotations only declare readOnly/openWorld/non-destructive; the description adds data-provenance caveats that annotations cannot carry, e.g. Cricsheet publishes no Afghanistan men's matches, so t20i/odi/test men's lists omit those players, and which leagues mix men's and women's games. That is genuinely useful for interpreting results. It does not describe ordering, pagination, or what happens on an unknown league code.

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 purpose sentence is correctly front-loaded, but the remaining text is an unstructured wall of semicolon-clause taxonomy that is hard to scan and repeats the schema's gender/members wording. Most sentences do carry information, so it is dense rather than padded, but it is not well organized.

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 6-parameter tool with no output schema, the description thoroughly covers the hardest dimension (league scoping, gender, members) but omits other things an agent needs: the sort direction (are leaders returned highest-first?), the meaning of 'kind' beyond the schema's one-liner, and the year format nuance. Return-shape omission is excused by the absent output schema, but ordering is not.

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 beyond the schema by defining the league taxonomy itself (t20 = T20Is plus code-less domestic T20; t20i = T20Is alone), which the schema only labels as 'league code, e.g. mlc, ipl'. It partially duplicates the gender and members semantics already in the schema, but the league expansion adds real meaning.

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?

Opens with a specific verb and resource: 'Leaderboards for a league and optional season: most runs or most wickets, from ball-by-ball archives.' That clearly separates it from siblings like cricket_player_career or cricket_phase_stats. It stops short of 5 because it never names a sibling it is not, so the agent must still infer the boundary against cricket_situational or cricket_minor_league.

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 bulk of the text is context for invoking the 'league' parameter correctly (t20 vs t20i, gender default behaviour, members 'full'), which is real usage guidance for a tricky dimension. But there is no explicit when-to-use-this-vs-alternative routing and no exclusions against the many sibling leaderboard-adjacent tools.

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