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

Annotations declare a safe read-only, idempotent, non-destructive operation, and the description still adds substantial behavioral detail beyond them: goalie-vs-own-stack prohibition, the one-skater-against-goalie allowance, 30-minute data refresh, DK-id-slot-ordered returns, and the caveat that own_lambda is a starting value rather than a contest-measured preset. That is rich context the structured fields do not carry.

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?

One dense paragraph, but it front-loads the roster shape and hard constraints first, then modes, then optional knobs. Given 13 parameters and no required fields, the length is justified; every clause conveys a constraint or default rather than filler, though the single-block format is slightly wall-of-text.

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 13-parameter optimizer with no output schema, the description covers the return contract ('Returns DK ids in slot order'), the constraint envelope, defaults, data freshness, and mode-dependent behavior. An agent has everything needed to invoke it correctly; no significant gap remains.

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 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: what happens when stack is empty (optimizer tries top stacks by 90th percentile and keeps the best), how min_unique interacts with a forced stack, and how contest_type drives the ownership model and multipliers. Useful elaboration beyond the individual field docs.

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?

States a specific verb and resource: 'Builds DraftKings NHL classic lineups' from 'the BankrollSZN projections', and enumerates the exact roster shape (C, C, W, W, W, D, D, G, UTIL under $50,000). The word 'classic' and the DK/salary framing distinguish it from sibling slates like invoke_nhl_showdown without needing to open a 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?

Gives clear in-tool usage context: gpp vs cash mode ('gpp scores ceiling minus an ownership penalty and stacks. cash scores the projection with no stack'), when to pass a stack versus leaving it empty for auto top-stack selection. It does not explicitly name sibling alternatives (e.g., the showdown optimizer) for other slate formats, so it is clear context without exclusions.

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