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

Annotations already declare readOnlyHint=true, so the description doesn't need to repeat that it's safe. It adds behavioral context: 'Free without a key (a capped slice of each). One email unlocks more of each; Pro unlocks the full board.' This discloses access tier limitations, which is valuable. However, it doesn't mention pagination, result size, or format of output, but given the read-only annotation and the tool's nature, the description adds some but not rich behavioral detail.

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 description is compact and front-loaded: it opens with the core purpose (gaps between model and ADP), then explains filters and access tiers, and closes with example searches. It's a single sentence but dense with information. Could be slightly more structured with separators, but it's efficient and free of fluff.

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?

Given the tool's moderate complexity (5 params, no output schema), the description covers the core value, filtering options, scoring/platform nuances, and access limitations. It lacks explicit details on what 'capped slice' means in terms of data volume, but the examples and overall guidance are sufficient for an agent to decide when to use it. The description complements the schema well without needing to explain return values.

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 input schema already describes all 5 parameters with 100% coverage, including descriptions for each (e.g., round filter, teams override, scoring enum, platform, position). The description adds some context by linking scoring/teams to platform defaults and noting best-ball for Underdog/DraftKings, but it doesn't explain how parameters interact (e.g., how round vs teams interplay). Since the schema does thorough work, baseline 3 is appropriate, with minor added value from 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 clearly states that the tool identifies sleepers and busts based on gaps between the PredictionMarketsPicks model and consensus ADP, with a specific verb 'gaps' and resource 'ADP for 2026'. It distinguishes itself from siblings by focusing on model-vs-ADP discrepancies, which is unique among the listed tools (e.g., draft_board, best_available). The inclusion of example search queries further clarifies its purpose for fantasy football draft analysis.

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 provides clear context on when to use the tool: for finding undervalued and overvalued players based on model vs ADP, and it mentions free access limitations. It doesn't explicitly say when not to use it or name alternative tools, but the context signals and the examples ('fantasy sleepers 2026', 'draft busts to avoid') make usage obvious. Lacks explicit exclusions or alternatives, hence a 4 instead of 5.

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