Compare two NFL players

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It accurately describes what the tool returns (a comparison of stats) and implies it is read-only, but it does not explicitly state that it has no side effects, does not modify data, or any limitations (e.g., data freshness, player name ambiguity). The description is not misleading and provides some outcome detail, but it lacks explicit side-effect or constraint disclosure. Given the read-only nature, this is adequate but not exceptional.

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 two sentences long and front-loaded with the core purpose and outputs. Every clause adds value, avoiding redundancy. It efficiently communicates the tool's function and usage context without unnecessary elaboration, making it easy for an agent to parse and act on.

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 comparison tool with no output schema, the description provides a solid list of returned information (points per game, volume stats, bye weeks, which produced more) and clearly states its intended use cases. It does not specify edge cases like season scope or player name handling, but these are minor and unlikely to hinder correct invocation. The description is comprehensive enough for an agent to understand what the tool does and when to use it.

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 provides 100% parameter coverage with detailed descriptions, so the description adds minimal new information beyond what the schema already states. The description does reinforce that 'scoring format' is used in the comparison, but this is already present in the schema's parameter description. Since schema coverage is high, the baseline of 3 is appropriate; the description does not need to compensate for undocumented parameters.

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 uses a specific verb ('Compare') with a clear resource ('any two NFL players head to head') and explicitly lists the outputs (points per game, volume stats, bye weeks, which produced more). This differentiates it from siblings like get_player (single player) and get_rankings (list-oriented) by emphasizing head-to-head comparison. The mention of fantasy football use cases further clarifies its niche.

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 states when to use it: 'Use this for start/sit, draft, and trade questions about two specific players.' This provides clear context and appropriate scenarios. It does not explicitly name alternative tools or exclusions, but the use-case framing implicitly distinguishes it from ranking or single-player tools. A minor gap is the lack of explicit 'when not to use' guidance.

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