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

With no annotations, the description carries the full burden. It transparently discloses the data source (predicates cited in each clearance's own summary), the time/number range (64,567 clearances, 1992-2026), and the exact output for both k_number (forward and reverse citations) and product_code (ranked predicates and recent clearances). It does not mention pagination or error behavior, but the data source and direction of results are well disclosed, adding significant context beyond what a generic query tool would provide.

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 information-dense yet efficiently structured. It opens with a clear one-line definition, then elaborates on the two query modes in separate clauses, and closes with use cases. Every sentence adds value, and there is no fluff or repetition. The structure is easy to scan and parse.

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?

Since there is no output schema, the description adequately explains what the tool returns for each parameter mode: k_number yields cited predicates and reverse citations, while product_code yields ranked predicates and recent clearances. It also mentions the limit parameter controls row count. Given the tool's complexity and the absence of an output schema, this description is comprehensive enough for the agent to know what to expect and how to use the tool effectively.

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?

Although schema coverage is 100%, the description adds substantial semantic meaning to each parameter. For k_number, it explains both forward ('what that device cited') and reverse ('which later devices cited IT') lineage. For product_code, it describes the output as 'predicates that code leans on most, ranked by how often they are cited, plus recent clearances.' This goes far beyond the schema's simple labels and gives the agent a clear understanding of what each parameter does and what results to expect.

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 tool's purpose: 'US 510(k) predicate lineage' with specific details about the data source (actual citations from summaries) and the two query modes (by k_number and by product_code). It explicitly distinguishes from similarity-based tools by noting it's 'not a similarity guess' and describes the reverse direction of citations, which clearly sets it apart from sibling tools like find_similar_devices.

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 use cases: 'Use when choosing a predicate, assessing substantial equivalence, or mapping who is clearing devices in a classification.' It implicitly contrasts with similarity tools by stating it's based on actual citations, but does not name specific alternatives or state when not to use it. This is clear guidance but could be stronger with explicit exclusions.

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