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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds behavioral context by explaining the nature of the searched statements (e.g., examiner's description, foreign wording) and the available modes (count, top_owners, list_marks, by_serial, statement_types), which goes beyond the structured annotations without contradicting them.

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 a single, dense paragraph with every sentence carrying useful information. It opens with the core purpose, then gives examples, outlines exclusions, and lists modes. It is slightly long but not verbose; no filler words or redundant restatements of the name.

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 tool with 8 parameters and no output schema, the description provides a comprehensive overview: it defines the statement types, gives example queries, lists modes (with one explicitly explained), and clarifies boundaries with sibling tools. It does not detail output formatting, but the mode names and examples give enough context for a user to understand what results to expect.

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?

With 63% schema coverage, the description compensates by explaining key parameters through concrete examples: 'text' is illustrated with 'PIZZA' and 'stripe', and 'statement_type' values are tied to real-world meanings (disclaimer, description, translation, prior_marks). The mode 'by_serial' is elaborated as 'every statement on one mark'. This adds semantic value beyond the schema entries.

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 uses a specific verb ('Search') and names the resource ('statements USPTO records on a trademark'), then enumerates the concrete statement types (disclaimer, description, translation, prior_marks). It also explicitly differentiates from sibling tools by referencing search_claimed_colors and search_trademarks, making the tool's unique scope unmistakable.

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 provides direct use cases ('Answers "which marks disclaim PIZZA"...') and explicitly excludes functionalities that belong to sibling tools ('Colour claims have their own tool...; goods text is served by search_trademarks'). It doesn't exhaustively cover all alternative scenarios, but the examples and exclusions give clear practical guidance.

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