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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real context: only ONE main line per player/market is returned (closest to even odds), not all available lines, plus a 20-minute refresh cadence. That prevents a common misinterpretation. It stops short of stating auth/plan constraints beyond what the schema for 'limit' already says.

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?

Front-loaded with the what/scope, then return fields, then the sign convention for bsz_minus_line, then refresh cadence. Dense but each clause carries information; slightly long for a single unbroken paragraph but no filler sentences.

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?

There is no output schema, so the description carries the full load of explaining returns — and it does: markets, one line per player/market, over/under odds, no-vig probability, projection, gap sign convention, and projected minutes. Combined with fully documented filter parameters, an agent has everything needed to call and interpret 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?

Schema description coverage is 100%, so all five parameters (team, limit, market, player, sort_by) are already documented, including the 'edge' sorting semantics. The description's market list mirrors the enum rather than extending it, so it adds little beyond the schema — baseline 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?

Specific verb+resource: 'NBA player prop lines for the next slate' with the exact markets enumerated, so an agent knows it returns market lines rather than pure model output. It does not explicitly name invoke_nba_projections (the sibling most likely to be confused with it), leaving differentiation to inference from the returned fields.

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?

Usage is implied by the content ('prop lines ... over and under American odds ... projection gap'), which suits betting/edge analysis, but there is no explicit when-to-use, when-not, or pointer to alternatives like invoke_nba_projections or invoke_odds_comparison. Adequate but leaves routing to the agent.

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