search_transactions

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower — yet the description adds a genuinely non-obvious constraint: the search runs against a single page only. That caveat plus the case-insensitive matching rule materially change how an agent must call the tool and are not derivable from the annotations or schema.

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 no filler: purpose first, then the critical single-page caveat, then a concrete usage example. The most important constraint (single-page scope) is front-loaded rather than buried.

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 and a mutation-free read tool, the description covers purpose, matching semantics, date scoping, and pagination behavior — everything needed to invoke it correctly. It does not describe the shape of returned transaction records, but for a search over an annotated read-only endpoint that is a minor gap.

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 is 3. The description earns an extra point by expanding what 'query' actually matches — merchant names, transfer descriptions, beneficiary names — beyond the schema's terser 'transaction details and beneficiary name', and by tying the date parameters to the keyword search.

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 and resource ('Search Ameria Bank transactions'), names the searchable fields (merchant names, transfer descriptions, beneficiary names), and scopes it to a date range. The keyword-search framing cleanly separates it from the sibling get_transactions, which implies unfiltered retrieval.

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?

Provides an explicit usage example ('how much did I spend on YANDEX this month?') and operational guidance to iterate pages or raise page size when full coverage is needed. It stops short of naming get_transactions as the alternative for unfiltered listing, so routing between siblings is left partly to inference.

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