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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description adds genuine context: results are exact model math rather than estimated real-game success, all optimal ties are returned, draw explanations are reconciled, and no recommendation is produced on incomplete jobs. The caveat about model vs. real-game success is exactly the kind of expectation-setting that prevents misuse.

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?

Three tight sentences with the central claim front-loaded and no filler; exclusions are appended efficiently. Slight cost from dense, undefined jargon, but every sentence carries information.

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 6-parameter, deeply nested, no-output-schema tool with zero schema descriptions, the description should explain the input contract and return shape. It covers the conceptual scope well but leaves the entire parameter surface and the result structure ('all optimal ties', 'reconciled draw explanations') undefined, which is a material gap for correct invocation.

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 0% across 6 parameters including a deeply nested state object, so the description carries the full burden and fails to document any parameter (contract_version, analysis_mode, explain_actions, budget_score_calls, request_id are all unmentioned). It gives no hint about the card-string encoding, the level structure, or what explain_actions accepts. The mention that ties/draw explanations are returned loosely implies explain_actions but adds no semantics.

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 conveys that this computes exact action values (play/discard choices) under optimal continuation for a small-deck model, which is a real verb+resource statement. However, phrases like 'the supported model' and 'exact_blind_survival' are never grounded, and it never plainly says it recommends the best action nor contrasts itself with evaluate_hand or compare_actions. Useful but leaves an agent inferring the core purpose.

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?

There is implied scope ('no recommendation on incomplete jobs', 'No A2/full-deck sampling'), which are exclusions of a sort, but they are stated as opaque jargon with no explanation of what A2 or a 'job' is. Nothing says when to call this versus compare_actions or evaluate_hand, and no prerequisites are given.

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