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

Annotations already define the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description only needs to add context beyond that. It adds that the output is 'invoice summaries with status and totals,' which clarifies the shape of results without relying on an output schema. It does not mention pagination or auth rates, but this is a read-only list and the annotations shoulder much of that burden.

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?

Three short sentences deliver high-value information with no redundancy. The opening sentence centers the use-case scope, the second defines the return shape, and the third points to the sibling alternative. This leaves zero waste and delivers all key selection criteria immediately.

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 moderately complex tool with 5 optional parameters, no output schema, and a clear read-only nature, the description covers the main usage scenarios, the output (summaries with status and totals), and distinguishes from invoice.get. It could potentially mention sorting, pagination, or parameter interplay, but the schema already supplies those constraints. Overall, the agent can correctly decide when to invoke and broadly understand what to expect.

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 coverage is 60%, so the description must partially compensate. It adds meaning to client ('specific client's invoices'), status ('outstanding, overdue, paid, drafts') and dates ('sent this month'), linking user scenarios to parameters. It does not explicitly explain 'limit,' but the schema already provides min/max and no required parameters, so the mapping is adequate.

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 (list), resource (invoices), and provides a comprehensive list of user intents (outstanding, overdue, paid, drafts, sent this month, client-specific). It also distinguishes itself from invoice.get by noting that it returns summaries and delegates line items to the sibling. Agents can readily identify when this tool fits without opening schemas.

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 gives explicit guidance: 'Use this when the user asks about invoices' and lists concrete query patterns (outstanding, overdue, paid, drafts, sent this month, which clients owe money, specific client). It explicitly points to the alternative: 'Use invoice.get for line items,' which addresses the main sibling. No when-not conditions are missing for this list-focused tool.

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