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

Annotations only provide basic hints (readOnlyHint=false, etc.), and the description adds meaningful context: it creates a draft, marks unbilled entries as invoiced (a behavioral side effect), and is non-destructive in terms of sending. It doesn't cover idempotency (annotations say false), but that's already hinted. The description adds value by explaining the draft-only nature and the marking behavior.

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?

The description is three sentences, front-loads the trigger context, then the key behavior ('draft only'), and ends with actionable guidance. Every sentence adds unique information; no fluff.

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 tool with 6 parameters, no output schema, and moderate complexity, the description provides essential context: draft behavior, inclusion of unbilled entries, and next steps. It doesn't mention error conditions or return format, but the description's guidance is sufficient for an agent to invoke it correctly and interpret the result as a draft.

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 50%, with parameters like due_in_days and through_date having defaults in the schema description. The tool description doesn't repeat parameter details but implicitly explains that through_date determines which entries are included. Since half the parameters are documented in schema, and the description clarifies the core semantics (including 'all unbilled entries'), it compensates reasonably.

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 clearly states the verb (create), resource (draft invoice), and scope (all unbilled billable entries for the client), and distinguishes it from sending via invoice.send. It is semantically rich and unambiguous, matching the title and name while adding functional detail.

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 description explicitly says when to use this tool (invoice request, billing period, unbilled hours), and directs the agent to use invoice.send when the user asks to send, providing a clear alternative. It also notes that nothing is sent, guiding expectation management.

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