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

Annotations already cover read-only, idempotent, non-destructive behavior, so the bar is lower. The description adds valuable behavioral nuance: what 'decision (SESE=cleared)' means, the regulatory meaning of a 510(k) clearance (substantially equivalent to a predicate device), and the data source/scope (175,000+ records, US public domain). No contradiction with annotations.

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?

Four sentences packed with useful information: action, return fields, filter targets, regulatory meaning, use cases, and provenance. Front-loaded with the verb and resource, no filler, and each sentence earns its place.

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 read-only, zero-required-param search tool with a full output schema and 100% schema parameter coverage, this description is complete. It covers what the tool returns, how to filter, why the data matters, and where it comes from. No critical gaps remain for an agent to invoke it 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?

The input schema fully documents skip, limit, and search with examples, so the baseline is 3. The description adds practical guidance by naming the specific searchable fields (device name, k-number, applicant, product code) and clearance type values (Traditional/Special/Abbreviated), which helps an agent construct meaningful Lucene queries beyond the schema's generic syntax.

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 and resource ('Search FDA 510(k) premarket clearance submissions') and enumerates the return fields and filter dimensions, making the tool's scope unmistakable. It also differentiates from sibling tools in the openfda_devices namespace (recalls, adverse_events, classification) by name and content emphasis.

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?

Provides clear usage context ('Useful for market research, competitive analysis, and regulatory pathway planning') and describes what can be filtered (device name, k-number, applicant, product code). It does not explicitly name alternative tools or when-not-to-use conditions, but the context is strong enough for an agent to infer appropriate invocation.

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