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

Annotations only cover readOnly and openWorld, so the description carries real weight here and delivers: explicit exclusions (no contacts, addresses, or label text), a stated cost of $0.0045 USDC via x402, and the failure behavior (unpaid calls return x402 payment requirements, retry with X-PAYMENT, PAYMENT-SIGNATURE, or params._meta['x402/payment']). That is exactly the kind of paywall/retry detail an agent cannot get from structured fields; only pagination-over-limit behavior is left unstated.

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 what the tool returns, followed by scope exclusions, then the payment mechanics in the order an agent needs them. Sentences are short and waste little, though the telegraphic 'K numbers, dates, product code and decisions' fragment is slightly clipped relative to the rest.

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 two-parameter, read-only lookup with no output schema, the description covers returned fields, data exclusions, cost, and the exact retry path after an unpaid call. Nothing essential is missing, though a note on result ordering or default result count would fully close the loop.

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%, so the query and limit fields are already documented and the baseline would be 3. The description earns the extra point by documenting the x402 payment channel, including the exact header names and the params._meta['x402/payment'] path, none of which appear in the input 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?

Opens with a specific resource plus its source: 'Official openFDA 510(k) device-clearance factual metadata by device name,' and enumerates the returned fields (K numbers, dates, product code, decisions). This lets an agent distinguish it from recall- or compliance-oriented siblings, though it never names an alternative tool explicitly.

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?

Usage is implied by the scoping sentences: it returns clearance metadata, not recalls or approvals, and 'Clearance is not premarket approval or medical advice' bounds the domain. However, there is no guidance on when to pick this over us_fda_recalls or product_compliance_checklist, so the agent must infer routing from sibling names.

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