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

Annotations already establish readOnly, non-destructive, closed-world behavior, so the description's job is to add domain context, which it does well by defining exactly what counts as 'spend' (settled, net of returns and reversals) versus what is excluded (in-flight, cards, fees). It does not mention auth/permission requirements or result size/pagination, which keeps it from a 5.

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?

A single dense sentence that front-loads the verb and resource, then nests clarifications in a parenthetical. Every clause earns its place, though the heavy parenthetical makes it a run-on that is slightly harder to parse than it needs to be.

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?

Return values need no explanation because an output schema exists, and the read-only annotation covers the safety profile. However, the description leaves the scoping parameters (especially companyId and signerId) unexplained, which is a real gap for a query whose entire correctness depends on that scoping.

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?

With 0% schema description coverage, the description must carry parameter meaning, yet it only gestures at an 'optional time window' (since) and never explains signerId or companyId, which are the critical scoping inputs for an agent's spend query. Two of the three parameters are effectively undocumented.

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 (Read) and resource (agent's settled spend) and then precisely delimits it: transfers the bank settled, net of returns and reversals, excluding in-flight transfers, cards and fees, broken down by counterparty and rail. An agent can distinguish this from read_transactions or card_get_card_spend without opening any schema.

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 scoping language ('settled spend', 'in-flight transfers, cards and fees excluded') implicitly tells the agent this is not for card spend or pending transfers, but no sibling is named and there is no explicit when-to-use/when-not guidance. The agent must infer that card_get_card_spend or read_transactions covers the excluded cases.

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