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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, covering the safety profile. The description adds only that this is a single-record fetch by Id; it omits not-found behavior, company-selection semantics, and any rate or error context. With annotations doing the heavy lifting, this is an appropriate 3.

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 front-loaded sentence with no wasted words. The trailing usage condition is compact and earns its place by constraining when the tool should be called.

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 single-record read with full parameter schema coverage and complete safety annotations, the definition is nearly complete. It lacks return-value context (no output schema exists) and not-found behavior, which keeps it from a 5.

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 both the required id and the optional company parameter are already documented in the schema. The description reinforces the required id ('by Id') but adds no syntax, format, or company-selection detail beyond the schema, so the 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 (Get), resource (bill), source (QuickBooks Online), and retrieval key (by Id), and the trailing clause distinguishes single-record retrieval from search or write alternatives. An agent can tell this apart from search_bills without opening either 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 clause 'when no search or write answer already holds it' gives a clear when-not condition, directing the agent to prefer existing search or write results. It does not name the specific alternative tool (e.g., search_bills) or explain how to obtain the required Id, so it stops short of explicit alternative routing.

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