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

Annotations already establish readOnly, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: starting goalies are checked first, prices are compared against a 10,000-season simulation, Polymarket is flagged as the international book, and the data is free — all context the agent could not derive from 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?

The front-loaded trigger phrases are well placed, but the remaining text is a dense stack of em-dash clauses and jargon ('Market · Model · Fair', '10,000-season sim', 'international book') that takes effort to parse. It is compact but not cleanly structured, and a reader must re-read to separate the market modes from the marketing framing.

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?

For a three-parameter, zero-required, read-only query tool with no output schema, the definition covers what an agent needs: the data domain, the market-mode routing, and the freshness guarantee on goalie checks. The absence of any hint about the returned row shape (beyond the terse 'Market · Model · Fair') is the only real gap.

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%, so the baseline is 3. The description does add real meaning for market=goals (anytime and first-goal contracts) and market=futures (Cup, conference and division markets), but team and limit are left entirely to the schema, making this net marginal rather than supplemental.

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 names a specific resource and scope — tonight's NHL games on Kalshi across moneyline, puck line, totals and period markets — plus the three market modes, so the agent knows this returns a model-vs-market board rather than a computation. It doesn't explicitly differentiate itself from siblings like calculate_ev or find_arbitrage, leaving the inference that this one surfaces data while those compute on it.

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?

It supplies concrete trigger phrasings ('NHL predictions tonight', 'Stanley Cup odds') and ties each market= value to the scenario it serves (game = tonight's board, goals = player props, futures = Cup/season markets). It never states when not to use it or which sibling to prefer for derived math, so routing against calculate_ev or kelly_size is left implicit.

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