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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine, non-redundant behavior: the call yields no file in this build, which saves the agent from treating an empty result as a successful download. It stops short of saying whether the call errors or returns an empty payload.

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 short sentences with zero filler; the capability statement comes first and the build caveat second, which is the right order.

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 one-parameter, annotated, no-output-schema tool, the definition covers what the agent needs to know about this tool's own behavior. What is missing is the surrounding context an agent actually needs when a tool is stubbed out: which sibling to call instead for invoice content.

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% and the schema itself states the invoiceId is "Ignored until phase 2," so the description adds nothing beyond it. Baseline 3 applies where the schema does the heavy lifting for a single required parameter.

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 names a specific verb and resource ("Returns an invoice PDF") and immediately qualifies it with the build limitation. It does not differentiate from the most confusable sibling, get_invoice, which likely exposes the same invoice data in a different form, so an agent still has to infer the distinction.

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 a strong when-not-to-use signal ("Not available until phase 2, and this build returns no file"), which is more exclusion guidance than most definitions offer. However, it does not route the agent to an alternative such as get_invoice or list_invoices, so the agent is left without a next step in this build.

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