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

Annotations already cover readOnly/idempotent/non-destructive/not-open-world, but the description adds genuinely new traits: it returns cited claims, inference labels and dated records, marks partial readings with withheld sections, preserves records on AI failure, and rejects supplied rates. This is useful behavioral context beyond the structured fields.

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?

It is a single dense sentence chained with semicolons; reasonably compact with no filler, but the information is not front-loaded into scannable clauses, mixing purpose, scope and output behavior into one run-on.

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 usefully describes the return shape (cited claims, inference labels, dated records, partial readings), which offsets some complexity from 8 parameters. However, it leaves the full parameter set and the required call preconditions unexplained, so it is only partially complete.

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 only 25% across 8 parameters, so the description is expected to compensate — but it explains none of amount, payment, loanKind, depositKind, loanKey, depositKey or question. Its only parameter-adjacent statement, 'No supplied rates accepted', is a constraint with no corresponding input to disambiguate.

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 ('an evidence-checked AI reading of bank_position') and enumerates its scope (savings/term deposits vs home, card, personal, car, business loans), which lets an agent distinguish it from the raw bank_position tool. The verb is implied rather than stated ('reading' rather than 'analyzes'), but the intent is legible.

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 no explicit when-to-use guidance: nothing says to call this after bank_position or find_products, nor when to prefer it over siblings like compare_rates or rate_details. The prerequisite (institutionId from find_products) lives in the schema, not the description, so usage must be inferred.

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