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

Annotations only say the operation is not read-only, not idempotent, and not destructive. The description adds valuable behavioral context: it creates a mutable draft (not a final document), returns a generated identifier, can be blocked by duplicate detection (implied by duplicate_ok), and is subject to a free-tier limit. It does not explicitly mention side effects like persistence or confirmation requirements, but the draft lifecycle is clearly communicated.

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 compact, front-loaded with the primary action and outcome, and every clause earns its place: it covers the data captured, the return value, the draft lifecycle, sibling routing, and the free-tier limit in three sentences. No filler or repetition of schema details.

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?

Given 23 parameters, 100% schema coverage, and no output schema, the description covers the essential context: what the tool does, what it returns, how the result relates to sibling tools, and a quota hint. It could be slightly more complete by explaining what happens on duplicate or invalid input, or by noting that sales can be deleted, but the core context an agent needs to invoke it correctly is present.

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%, and the description adds meaningful context beyond the schema by grouping fields conceptually (who sold, who bought, what item, price in minor units, date) and explaining the returned document number. It also clarifies that price_minor uses integer cents with an example. Most parameters are fully described in the schema, so the description does not need to repeat every field; the added context is useful without being redundant.

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 opens with a specific verb and resource ('Record a sale') and immediately states the outcome ('generate the bill of sale'), listing the exact data fields involved and the returned artifact ('BOS-YYYY-NNNN number of the draft'). It distinguishes itself from sibling tools by naming sale_update, sale_finalize, and sale_render and clarifying the draft lifecycle, so an agent can tell it apart without inspecting 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 explicitly defines when to use this tool: to record a sale and create a draft. It names the exact siblings for later operations—sale_update for changes, sale_finalize for freezing into the signing copy, sale_render for printing—and includes a free-tier constraint ('Free tier: 10 drafts'). It also highlights key options like duplicate_ok and as_is defaults, providing clear context and exclusions.

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