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

Annotations already establish readOnly=false, so the non-read-only nature needs no credit. The description adds useful context: it returns the float id, defines imprest as the replenishment target, and notes the free-tier limit of one float. It does not discuss the side effect that calling twice opens two floats despite idempotentHint=false.

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 with no filler. The core action, return value, key concept, and constraint are all included efficiently, and the most important information is front-loaded.

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?

For a simple creation-style tool with 6 parameters whose schema covers most of them, the description is largely complete: it states the output (id), a key business rule (free tier: one float), and clarifies the imprest concept. It would be slightly stronger with an explicit note about not using it for existing floats or replenishments, but that gap is mostly captured by the usage dimension.

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 83%, so the baseline is 3. The description adds genuine semantic value by explaining imprest_minor as the amount the tin is 'topped back up to at every replenishment,' which goes beyond the schema's 'float amount in whole minor units'. Other parameters rely on the schema's adequate descriptions.

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?

The description states a specific verb ('Open') and resource ('petty cash float on the imprest system') and tells the caller it returns the float id. It is clear and unambiguous, though it does not explicitly contrast itself with lifecycle siblings like replenish_request or reconcile.

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?

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'topped back up to at every replenishment' hints that opening precedes replenishment, but the description never states 'use this for a new float, not for top-ups or reconciliations' or similar.

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