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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior beyond that: newest-first ordering, the sign convention for amountUsd (negative=charge, positive=top-up/adjustment), and an explicit non-effect statement. The sign convention is the kind of domain semantics an agent cannot get from 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?

Three sentences, all front-loaded and dense: scope first, then the amount sign convention, then the return shape and the explicit non-behavior. No filler, and the field list earns its place because there is no output schema.

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 burden of describing return values and does so concretely: account_id, transactions with source/description/referenceId/createdAt/markup, plus total_elements, total_pages and page. Combined with the amountUsd sign semantics and empty-required-params, an agent has enough to call and interpret the result. Minor gap: no mention of default page size behavior when handing off to a follow-up page request.

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% with only two optional parameters, so the schema already documents page (zero-based, default 0) and size (1-100, default 25). The description reinforces ordering ('newest first') and that page 0 is the most recent, but adds no syntax or constraint detail beyond the schema. 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+resource with scope and ordering: 'Read paginated AI credit movements for the authenticated account, newest first.' An agent can distinguish this from mutation/purchase tools, and the closing line 'This tool does not initiate a purchase' further narrows it. It does not explicitly distinguish itself from the sibling get_credit_balance, which is the nearest alternative.

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 rather than stated: the tool reads movement history, and the negative statement about not initiating a purchase functions as a partial when-not hint. However, it never names get_credit_balance or get_payment_status as the alternative for a current-balance or billing question, leaving the agent to infer the routing.

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