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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real behavioral detail beyond them: the exact per-row contents (consensus line, projection, gap, lean, over probability, book probability, best odds, each book's line) and the two distinct result modes. It omits plan-limit or rate-limit behavior, which only appears in the schema.

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 source and comparison, then the row contents, then the two invocation modes. The market enumeration is long but directly useful for choosing the market parameter, so it largely earns its place.

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?

With no output schema, the description carries the return-shape burden and does so by listing every returned column, which is the key missing piece. For a 9-parameter, zero-required tool it leaves only minor gaps such as how limit interacts with the plan limit and team/date scoping.

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 coverage is already 89%, so the baseline is 3, but the description adds genuine semantics: player matching returns the full stat projection (a mode interaction across parameters, not just a filter), and the no-player default surfaces the biggest gaps. It does not explain team, min_books or include_started beyond the schema text.

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?

States a specific verb/resource: this week's NFL player props from named sportsbooks placed next to BankrollSZN projections, with the market list spelled out. It contrasts book lines against model projections, which implicitly separates it from invoke_nfl_projections, but it never names a sibling tool to make that distinction explicit.

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?

Gives clear usage context for the two modes: pass a player to get every prop plus the full stat projection, omit a player to get the biggest gaps. It does not state when a caller should prefer this over invoke_nfl_projections or the league-agnostic invoke_odds_comparison, so there are no exclusions or named alternatives.

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