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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds value by explaining the lookback window behavior (default 24h, max 7d), the sorting criteria (absolute movement), and the tiered access (free is locked, Builder vs Pro). It does not mention any potential delays or data freshness, but for a read-only scanning tool this is adequate. A high score is justified because it enriches beyond annotations.

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 fairly concise and front-loaded: the main purpose is in the first sentence. The usage guidance is structured clearly with 'When to use' and 'When not to use'. However, the tier information (free locked, Builder board) is somewhat tangential to the tool's direct usage and adds a bit of noise. Overall, it's well-organized and efficient.

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?

The description covers the tool's core function, lookback parameters, sorting, and usage scenarios. It does not detail the output format, but since there is no output schema, an agent might wonder what the response looks like. However, for a scanning tool, the description provides enough to call it correctly, including hints about the 'since' parameter's format. The tier information is extra context but not necessary. Overall, it's complete for practical use, missing only explicit return shape.

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 75%, with descriptions for stat, since, and sport, but not for limit. The description adds context for the 'since' parameter by explaining the lookback window and its constraints, which is useful beyond the schema. However, it does not explain 'limit' semantics beyond what the schema states (max 500, min 1). Since coverage is high, baseline is 3, and the added context is minimal, so a 3 is appropriate.

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's purpose: to list props whose lines moved the most within a lookback window, sorted by absolute movement. It specifies the resource (props), the action (scan for movers), and the distinguishing feature (movement focus). This differentiates it from siblings like scan_props (current board without movement) and get_prop_history (history of one prop).

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?

Explicit 'When to use' and 'When not to use' sections provide clear guidance. It gives natural language examples ('biggest movers', 'which lines moved the most today') and names alternatives (get_prop_history, scan_props) with their contexts. This leaves no ambiguity for the agent.

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