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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description only needs to add context. It reinforces 'Creates nothing' and adds return content ('lines, hours, and total') and equivalence to create_draft. It doesn't cover error behavior or tax handling, but the lower annotation bar makes this a 4.

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?

Two sentences with no filler: the first gives the use case, the second states side effects and output. Every sentence earns its place 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?

There is no output schema, so the description correctly summarizes the return shape ('lines, hours, and total'). It also communicates the no-side-effect nature and default date behavior indirectly via 'unbilled entries'. Missing details like tax handling and error cases are minor given the schema defaults and annotations.

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 75%, so the description carries a modest burden. It adds meaning by saying the same arguments would produce a create_draft result, but it doesn't explain the undocumented tax_rate_percent or provide any parameter-level detail beyond the schema. This is mild added value, so a 3 is appropriate.

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 uses a specific verb ('Preview') plus resource ('invoice') and clarifies the scope: unbilled work for a client. The final sentence explicitly ties the output to invoice.create_draft, which distinguishes it from the sibling tool 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?

It opens with an explicit trigger: 'Use this when the user asks what they could invoice a client for...'. 'Creates nothing' functions as a when-not signal, and the reference to invoice.create_draft routes the agent toward the actual creation alternative.

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