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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true), so the bar is lower. The description adds useful context beyond them: that the call is reversible via null ('mark it unpaid again') and why the date matters (cash-basis tax treatment). It does not discuss permissions or audit behavior, but for a two-parameter setter that is minor.

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?

A single sentence that front-loads the primary action and appends the inverse case. No filler, no repetition of the title, nothing that could be cut without losing information.

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?

An output schema exists, so return values need no explanation, and the annotations carry the idempotency and safety profile. Both modes of the operation and the date format are covered, so an agent has everything needed to invoke this correctly.

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 100% — both 'invoice' and 'paid_date' are documented in the schema, including the YYYY-MM-DD format and null option. The description's 'pass null to mark it unpaid again' largely restates the schema's 'null for unpaid', so it adds rationale rather than new parameter semantics. Baseline 3 is correct.

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 (record the paid date) on a specific resource (an invoice), and covers both directions of the operation — set paid or null to unmark. An agent can distinguish it from get_invoice, list_invoices, and create_invoice 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?

Gives clear context for when to use it (recording a payment date, which matters for cash-basis taxes) and explicitly describes the inverse case via null. It names no sibling alternatives, but no sibling competes for this action, so the absence is not a real gap.

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