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

Goes well beyond the readOnlyHint annotation by disclosing sort order (company name), the absence of dates and therefore the inability to answer recency questions, the exclusion of draft-only recipients, and the fact that the list is not paginated. These are exactly the traits an agent needs to avoid misusing the result.

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?

Front-loaded with purpose and returned fields, then caveats. Every sentence carries non-redundant information: what it returns, when to use it, sort order, exclusions, and no-pagination behavior.

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 no output schema and no parameters, the description must carry both intent and result shape, and it does: it names the returned fields, the deduplication rule (latest finalized invoice), and the limits (no dates, no drafts, no pagination). Nothing an agent needs to call or interpret it is missing.

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?

The tool takes zero parameters, so the baseline is 4. The description usefully describes the shape of each returned recipient (address, VAT ID, email, invoice number from the latest finalized invoice), which compensates for there being no output schema.

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 ('Lists the customers the account has invoiced') and immediately qualifies it with the exact fields returned, which separates it from a generic customer list. It does not explicitly name list_customers or get_customer as the alternative, so the sibling distinction must be inferred rather than read.

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?

'Use it to look up a customer's details before creating an invoice' gives a concrete trigger tied to a sibling action (create_invoice). What is missing is an explicit contrast with list_customers/get_customer for the same lookup, so the agent still has to reason about which list to call.

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