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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them by disclosing the return payload shape, the 500-payment cap, the 'unresolved with no amount' degradation path, and the meaning of withheld_is_estimated. It does not mention auth requirements, rate limits, or the error behavior when both/neither input is provided.

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?

One dense paragraph that front-loads the purpose, then input modes, then return shape and edge cases — every sentence carries information. It is close to a run-on, but nothing is redundant or padded.

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?

With no output schema, the description steps up and documents the returned fields (source country, treaty rate, reclaimable amount, form, deadline, per-country totals) plus the unresolved and estimated-withholding flags. Combined with the covered parameters, an agent has enough to call it and interpret results 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 coverage is 83%, so the schema already carries most parameter meaning; the description adds the coupling that broker must accompany csv_text and enumerates the payment fields (ISIN, payment_date format, gross_amount, currency, optional withheld_amount). column_map and residence_currency handling 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 (estimate), resource (reclaimable withholding tax across a dividend history), and scope ('a whole dividend history in one call'), which implicitly separates it from the single-refund sibling estimate_refund. An agent knows exactly what this computes without opening the 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?

Explicitly prescribes the two invocation paths — "send either a broker export as csv_text with its broker id, or a list of payments" — which is real routing guidance the agent would otherwise have to infer. It stops short of saying when to prefer this over estimate_refund or what to do if neither input is supplied.

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