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

Annotations (readOnly, idempotent, non-destructive) already cover the safety profile, so the bar is lower, and the description still adds rich behavior: mandatory QB stack and bring-back, the DST-vs-QB exclusion rule, gpp scoring ceiling minus ownership penalty vs cash projection, exact search, and 'returns DK ids in upload order'. Only runtime/rate-limit details are absent, keeping it just below a 5.

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?

Dense but front-loaded: it leads with what is built (lineup/cap/roster) before construction constraints and scoring models. Every sentence carries information, though the jargon-dense middle ('bring-back in the shapes of the contest preset') is harder to parse than the opening.

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?

It covers output format ('DK ids in upload order') well enough given no output schema, and explains construction constraints. But for a 15-parameter tool with 0% schema coverage and no annotations explaining params, the definition is not complete enough to guide correct invocation of most arguments.

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?

With 15 parameters and 0% schema description coverage, the description must carry the burden, but it only indirectly illuminates a few: mode (gpp/cash scoring), contest_type presets, bring_back/stack shapes, and allow_dst_vs_stack via the DST rule. Names like lock, exclude, slate_id, min_salary, min_unique, own_lambda, max_total_own, and min_projection are left entirely undefined.

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 states a specific verb+resource ('Builds DraftKings NFL classic lineups') with the exact cap, roster slots, and construction rules. This clearly distinguishes it from sibling optimizers (e.g., invoke_nfl_showdown, invoke_mlb_optimizer) without the agent needing to open any schema.

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 implies usage through the gpp/cash mode contrast and the 'same presets as the site NFL optimizer' framing, giving a sense of context. However, it never explicitly states when to choose this tool over alternatives such as invoke_nfl_showdown or invoke_nfl_sim_picks, nor when to prefer gpp vs cash. Usage is implied rather than prescribed.

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