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

The description details the gated/free structure ('Free without a key—a capped slice'), what unlocks with an email, with Pro, the boom/bust weekly odds and position tier. That discloses a real gating/unlock side-effect beyond the structured fields. It also lists the return value semantics ('the single biggest model value left') but no need to specify, and no description says 'read-only'—with no annotation hazards, but behavior is one reason enough.

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 packed. It is about 190 words (the description is 193 words). That is a longish description, covering a lot of details and structure, but all relevant: trigger and results, plus tiers of differentiated data. It is ein struktureller, but not an 'economical' one. 4.

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?

There is no output schema, and the description does not define the return structure beyond 'best players left' and the list's entries are included with projection, ADP, and flag. However, it does not define order/sorting, the shape of the output object, the list of results, or the exact field names. It gives the result shape, but it is incomplete for a tool of this complexity and with 6 parameters.

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?

The schema has 6 parameters at 100% coverage and each description provides semantic depth: 'teams' describes size calculation for draft-round math (overrides the 12-man league default), 'roster' describes player names on the user's team to enable the bye-week warning, 'drafted' is used to exclude picked players, 'scoring' selects the format, and 'platform' selects the platform. The description provides context beyond the schema, by indicating what each parameter does, not using the description.

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 ('return') and resource ('best players still on the board') with clear scope ('2026 season, any scoring format'), and defines its niche as a mid-draft tool for choosing the best available player. It differentiates from sibling tools by naming its preferred trigger queries ('who is the best available', 'who should I take next', 'best player left'), earning it a 5 for purpose clarity.

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 description gives a usage preference: 'Prefer this mid-draft when the user asks...' which is explicit. It doesn't explicitly say 'don't use this when X', but does include alternate context ('mid-draft'), so it conveys a clear usage context without explicitly excluding alternatives. A 4 is correct.

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