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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description goes further by disclosing the validation contract: exactly one method, no defaults, and an INVALID_ARGUMENT error envelope rather than an exception. That failure-mode disclosure is real value beyond the annotations. One caveat: 'no defaults' is in mild tension with the schema, which lists default null for every optional field, so a 4 rather than a 5.

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-loads purpose, then exclusions, then the per-method input contract, then the error contract — a sensible priority order with no filler sentences. The middle method-inventory sentence is dense and list-heavy, but every element is load-bearing rather than decorative.

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 15-parameter tool with an enum discriminator and an output schema, the description supplies the method-to-input contract, the mutual-exclusion rule, the sibling routing, and the error behavior. Return values are covered by the output schema, so nothing an agent needs to invoke this correctly is missing.

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 would be 3, but the description adds the crucial conditional mapping the flat schema cannot express: which inputs each method value requires (discrete: outcomes+probabilities; continuous: distribution/mean/std/lower/upper; monte_carlo: iterations/distributions/base_params/seed, etc.). This resolves the cross-parameter dependency the enum alone leaves ambiguous.

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?

It names a specific verb and resource ('expected-value engine', 'Compute expected values') and immediately scopes the breadth of methods it covers. It distinguishes itself from sibling tools by name, explicitly ruling out calculate_actuarial_pv and calculate_structured_product, so an agent can route between them without opening any schema.

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?

Explicit when-to-use ('generic probability weighting of scenarios, Monte-Carlo and decision trees') and two explicit when-not cases with the correct alternative tool named for each. Nothing about selection is left to inference.

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