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

Annotations already establish readOnly/idempotent/non-destructive, and the description layers on meaningful extra context beyond them: the data refresh cadence (every 30 minutes), the derivation method (de-vigged sportsbook market plus opponent-adjusted strike/takedown/control rates), and a backtest benchmark (30.9 vs 35.6 mean miss). This is well beyond the annotation-implied safety profile.

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 a one-line statement of what the tool returns, followed by context. The field enumeration and methodology/backtest sentences are dense but each carries information an agent needs (returned columns, provenance, freshness). Slightly long, but no clear waste.

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?

No output schema exists, so the description must convey the return shape — and it lists the per-fighter fields (projection, floor, ceiling, ownership, win/KO/submission probabilities, etc.) plus data source and refresh cadence. For a read-only projection tool this is complete enough to call correctly.

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 six parameters (site, limit, fighter, sort_by, slate_id, contest_type) are already documented in the schema, including enum meanings and defaults. The description adds nothing parameter-specific beyond a passing reference to 'the chosen contest type', so the 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?

States a specific verb and resource: UFC DraftKings/FanDuel projections for the next card. The DFS-specific fields it enumerates (salary, value per $1K, projected ownership, leverage-adjacent metrics) clearly set it apart from sibling tools like invoke_mma_odds, invoke_mma_elo and invoke_mma_fight_sim, which cover the betting and simulation angles separately.

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 only implied: it says 'for the next card' and mentions the slate/contest-type defaults, so an agent can infer this is the DFS-projection tool. However, there is no explicit when-to-use versus alternatives (e.g., invoke_mma_odds, invoke_mma_fight_sim, invoke_mma_optimizer) and no prerequisites or exclusions stated.

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