sportsdataio_nfl_projections

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

Annotations already declare readOnly, idempotent, and openWorld, so the bar is lower. The description adds substantial value by disclosing the shape is from vendor docs and unverified, advising to inspect actual payload. It also notes authentication requirements and per-operator scoring differences. This is transparent and goes beyond the annotations without contradicting them.

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 well-structured and efficient: a single purpose sentence, a return shape, a note, an example, and auth info. Each sentence earns its place—no fluff. The structure with 'Returns:', 'NOTE:', 'Example:', and 'Auth:' makes it scannable with all critical information front-loaded.

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?

Despite the absence of an output schema, the description lists the exact return fields, making the payload predictable. It also covers the data reliability caveat, an example call, and authentication. Given the tool's simplicity (2 params, no nested objects), this is a complete and self-contained description that answers likely questions an agent would have.

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 schema covers both parameters 100% but only describes them as 'Required — part of the URL path.' The description's example ({"season": "2023", "week": 1}) adds concrete format and type semantics, clarifying that season is a string like '2023' and week is an integer. This adds value beyond the minimal schema descriptions, though it could have explained the season format more explicitly.

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: 'Projected NFL player game statistics for a week.' This is specific, identifies the resource (NFL player game statistics) and the scope (projections for a week), and naturally distinguishes it from sibling tools like sportsdataio_nfl_scores or sportsdataio_nfl_teams. The return shape and example further reinforce the purpose.

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 gives clear context for use (projections for a week) and an example invocation. It also provides a usage hint about per-operator scoring columns ('DraftKings and FanDuel score differently, so use the matching one'). However, it does not explicitly state when not to use this tool or name alternative tools for other data types (scores, injuries, etc.), so it stops short of full exclusions.

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