Search transactions

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

The annotation already declares readOnlyHint=true, so the safety profile is covered. The description adds useful context: transfers excluded by default, pagination capped at 200. However, it doesn't disclose the return format, whether results are ordered, or what the total count semantics are for offset/limit. With readOnlyHint present, baseline 3 is fair; it adds some value over annotations but not deep behavioral detail.

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?

Two sentences, zero waste. Every clause carries meaning: the filter list, the transfer default, and the pagination cap all add value. Well front-loaded with the core search purpose first.

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 an 11-parameter search tool with no output schema and only 36% schema coverage, the description gives a solid high-level frame: filters available, transfer default, pagination cap. It doesn't explain result ordering or the relationship between offset/limit and any total-count concept, which would be helpful given no output schema. Slight gap, but the search semantics are reasonably complete for a list tool.

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 only 36%, so the description partially compensates by listing the filter categories. However, it doesn't add detail beyond the schema for ambiguous params like min_amount ('Units, e.g. -500' in schema) vs max_amount (no description in schema). It confirms search_text matches payee/notes and pagination limit, but doesn't resolve all gaps left by the 36% coverage.

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 uses a specific verb (Search) with a clear resource (transactions) and lists concrete filters (account, category, text, amount range, uncategorized). It also states two distinguishing traits: transfers excluded by default and pagination limit of 200. This clearly differentiates it from sibling read tools like get_spending_summary or get_net_worth.

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?

The description clearly states the search scope (date range with optional filters) and that transfers are excluded by default. It mentions the pagination max of 200. It doesn't explicitly name alternative tools or when-not contexts, but the read-only nature and filter set give a clear usage context. Could name a sibling like get_spending_summary as an alternative for aggregated data.

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