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

Annotations already declare readOnly/idempotent/non-destructive; the description goes further by disclosing the dispatch contract (one method, no defaults) and the failure mode ('unknown method, missing input, or extra field returns an error envelope code INVALID_ARGUMENT instead of raising'). That error-shape disclosure materially changes how an agent handles failures and is not available anywhere else.

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 routing, then the method/input table — a sensible order. The method listing is dense but earns its place given 13 enum values and 24 optional fields; a small amount of repetition ('notional, spot, maturity, risk_free' recurs) keeps the per-method rows self-contained.

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?

An output schema exists, so return values need no explanation. With purpose, sibling routing, method-to-input mapping, strictness rules, and error behavior all covered, an agent has everything needed to call this 24-parameter dispatcher 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 per-parameter units are already documented and the baseline is 3. The description exceeds that by mapping each of the 13 method values to its exact required input set, information the flat schema cannot express (the enum description even defers to it). It stops short of a 5 because per-parameter units/edge semantics are left entirely to the schema.

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 ('Value') and enumerates the exact instrument classes it covers (CBBCs, derivative/inline warrants, ELNs/ELIs, autocallables, accumulators, CLNs, TRS, CFDs). It explicitly contrasts itself with named siblings (calculate_option, calculate_convertible_bond, calculate_fixed_income), so an agent can route 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 ('equity-linked and credit-linked payoff structures') plus three named alternatives with the condition that selects each, and a dispatch rule ('supply exactly one method with its declared inputs'). Nothing about tool 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.