Sleeper league overview

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true), so the description's job is to add scoping context. It discloses exactly what league data is returned and, notably, flags that future pick ownership is 'calculated' derived data rather than raw stored data. It does not disclose aggregation cost or partial-failure behavior, but the content scope is the key behavioral trait for a read-only overview tool.

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?

Two sentences with zero filler: the first front-loads the full content list, the second adds a deliberate boundary. Every clause earns its place and the density-to-length ration is excellent.

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 tool with no output schema and ten sibings spanning overlapping domains (drafts, rosters, trades, transactions), the description supplies a usable category list but omits return sturcture, the time scope of 'records', and how pick_years interacts with the calculated ownership data. The roster exclusion helps disambiguate, yet an agent calling this tool is still guessing at the response shape for a fairly complex aggregation.

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 67% (league_id and pick_years have descriptions, username does not), and the description contributes zero parameter guidance. The 'username' parameter is left unexplained in both the schema and the description — an agent cannot tell whether it filters scope, authenticates, or is merely optional context alongside the required league_id. The description also never connects pick_years to the 'calculated future pick ownership' it mentions.

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 uses a specific verb ('Get') with a detailed content list — rules, scoring, lineup slots, team directory, records, drafts, traded picks, and calculated future pick ownership — that precisely scopes the resource. The exclusion clause ('Does not include every player on every roster') explicitly disambiguates it from roster-oriented sibings like sleeper_all_rosters. It stops short of 5 because it never names a sibing tool outright, relying on the 'overview' naming to carry differentiation.

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 content list implies this is the comprehensive league-level entry point, and the final sentence signals when not to use it (when complete roster data is needed). However, no alternative sibing is named and there is no explicit when-to-use/when-not-to-use guidance, leaving the agent to infer routing from the tool name and the exclusion clause.

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