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

Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-obvious traits: results are sorted widest-first, the call is free, and ADP gaps will not return until the 2027 offseason — a caveat that prevents the agent from mis-selecting this tool for an ADP request based on its name. Return format/pagination behavior is not described.

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?

Two compact sentences with zero filler; the season/scope constraint is front-loaded before the ADP caveat. Every clause carries information an agent needs.

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 should carry the return-shape burden, and it partially does via ordering and scope. Parameters are fully covered by the schema, and the seasonality caveat closes the largest ambiguity. Missing only a note on what fields/columns a gap row contains.

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 100%: limit (default 15, clamped at 50) and position (with FLEX semantics) are fully documented in the schema. The description only echoes the position filter and adds "widest first" ordering, adding marginal value beyond structured fields. Baseline 3 applies.

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?

Names a concrete resource (Kalshi vs book-consensus gaps on this week's NFL props) and states ordering and filtering scope, so the agent knows exactly what comes back. It does not explicitly contrast itself with close siblings like nfl_prop_edge or scan_mispricings, leaving the agent to infer the distinction. The title/name mismatch (adp_market_gaps vs a props tool) is resolved only by the parenthetical caveat.

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 leading "In season:" implies a usage window, but no alternative tool is named and no explicit when-not condition is given beyond the ADP caveat. The agent can infer this is the current-season props gap tool, but routing against nfl_prop_edge/scan_mispricings is left to guesswork.

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