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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe read operation and not a real-world interaction. The description adds that it is 'Free, no key' and provides a pick recommendation, which is useful context. However, it does not disclose what data sources are used, whether results are based on projections or historical data, or if there are any limitations (e.g., only 2026 season). It doesn't contradict annotations, but could offer more on how the recommendation is derived.

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 a single, information-dense paragraph that front-loads the core purpose and key outputs. It efficiently includes triggers and usage notes without unnecessary fluff. The only minor issue is that the list of examples could be seen as slightly redundant, but it still earns a high score for compactness.

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 (3 parameters, no output schema), the description covers the essential use cases, trigger phrases, and key features. Annotations handle safety, and schema covers parameter details. It lacks explicit mention of what the output format looks like (since there is no output schema), but the description's mention of 'pick recommendation' and 'best market value' gives enough expectation. It could be more complete with a note on data sources, but overall it is sufficient for an agent to select and invoke it correctly.

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 schema already documents all three parameters with clear meanings (players, scoring, platform). The description adds context about scoring overrides and platform defaults, but it doesn't go much beyond what the schema says. It clarifies that 'scoring' overrides a platform preset and that Underdog/DraftKings are best ball, which is helpful, but the baseline of 3 is appropriate given high schema coverage.

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 the tool compares 2-4 players for a fantasy draft, with specific attributes (projection, floor/ceiling, ADP, draft round, value flag) and outputs (pick recommendation, best value). It distinguishes from siblings by focusing on head-to-head player comparisons, whereas siblings like 'adp_market_gaps' or 'best_available' target broader market or draft strategies.

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 explicitly lists example user queries that should trigger this tool ('<A> or <B> in fantasy', 'who should I draft, <A> or <B>'), and contrasts with alternatives by noting it is for side-by-side comparisons, not other drafting tasks. It also specifies draft context (2026 fantasy draft) and scoring formats, giving clear when-to-use guidance.

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