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

On top of the readOnly/idempotent annotations, the description adds real behavioral context: that levels are earned and no tool can raise one, and that recheck performs a live recompute of activity (card on file, paid bills, days active, real calls) rather than reading the saved value. These are non-obvious traits the annotations do not convey; return-shape detail is partly duplicative of the output schema.

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 purpose and default behavior are front-loaded, and every clause carries information. However, the prose is dense and run-on (a comma-spliced list of returned fields, then a long recheck sentence), so it is slightly harder to scan 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?

With an output schema present, return values need not be spelled out, and the description still covers all four focus modes, recheck semantics, and the immutability of levels—more than enough to call it correctly. It stops short of describing error/edge behavior (e.g. when a business is not accessible, or what 'hold' means operationally).

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 3 is the floor. The description exceeds it by explaining the intent behind recheck (recompute now, e.g. right after a card was added, matching the dashboard's stale-copy recompute) and the focus/level interplay, giving meaning the enum values alone do not.

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 ('Read one accessible business's trust level') and then enumerates exactly what comes back: current level, steps to next, unlocks, outbound usage against limits, and any hold. No sibling tool in the list deals with trust/progression, so it is unmistakably distinct.

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?

It gives clear when-to-use guidance for the internal modes ('focus "ladder" walks every level; focus "level" with level explains one') and a concrete trigger for recheck ('recheck=true ... instead of the saved level ... when its copy is stale'). What is missing is routing guidance against sibling tools such as get_usage or get_business_info, which an agent might otherwise confuse with usage/account reads.

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