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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior. The description adds substantial context beyond that: case-insensitive substring matching, a 12-month default window, pagination defaults and caps, the fact that totals cover all matches even when transactions are paginated, and a warnings array for banks that could not contribute, including reconnect_url.

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?

The description is front-loaded with purpose and packed with useful details; every sentence contributes. It is a single dense paragraph rather than clearly structured bullets, which is a minor readability cost but not wasteful.

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 carries the return-value burden and does so: it names the aggregate fields, explains transaction ordering (newest first), clarifies pagination vs. totals, and documents the warnings array. That is complete enough for an agent to call this tool 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 100%, so the baseline is 3. The description adds meaning beyond the schema: merchant matching is a case-insensitive substring against merchant name or description, the default window is the last 12 months, and limit/offset defaults and maximums are consolidated. It does not document account_id or exact start/end semantics beyond 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 resource ('charge history for one merchant') and enumerates the aggregate fields returned, so the agent knows exactly what this tool produces. It does not explicitly contrast itself with siblings like search_transactions or get_recurring_charges, which keeps it from a 5.

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: this is the tool for merchant-specific charge history, and the default 12-month window is stated. However, there is no explicit guidance on when to choose it over search_transactions or get_recurring_charges, and no exclusions are given.

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