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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real behavior beyond them: case-insensitive substring matching, newest-first ordering, an implicit 30-day default window, hard pagination caps, and a `warnings` array for banks that could not contribute including a reconnect_url. The partial-failure disclosure with reconnect remediation is exactly the kind of context an agent needs before trusting an empty result.

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?

Purpose and match semantics are front-loaded in the first sentence, which is the right priority. There is minor redundancy — two consecutive sentences open with 'The response includes', and limit/offset defaults are repeated from the schema — but nothing is wasted enough to impede reading.

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 correctly carries the return-shape burden by naming total_count, has_more, and the warnings structure. What remains unstated is whether the search spans all accounts by default and how the date window behaves when only one of start_date/end_date is supplied, which matters for a 6-parameter date-scoped 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 description coverage is 100%, so every parameter including limit, offset, start_date, end_date, and account_id is already documented in the schema. The description restates the pagination defaults and window but adds no new syntax, format, or edge-case meaning beyond what the schema provides; baseline 3 applies.

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 plus matching semantics ('case-insensitive substring match') and ordering ('newest first'), so the agent knows exactly what the tool does. However, it never distinguishes itself from the sibling list_transactions, which an agent could easily choose instead when it wants a transaction list.

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?

Usage is implied by the search semantics and by the stated default 30-day window, and the pagination guidance says to page with limit/offset. But there is no explicit 'use this when X, use list_transactions when Y' routing, and no guidance on when to supply account_id versus searching broadly.

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