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

The description discloses behavior beyond the readOnlyHint and idempotentHint annotations: it explains that status=live means registered and pending together, that top_terms with nice_class returns per-term mark counts, and that a registered-only ranking is not available (only a single term's count via mode=count). This is rich, non-obvious behavioral context an agent needs to call correctly.

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 long but information-dense, with no filler. It is front-loaded with the core purpose, then examples, then mode specifics. All sentences earn their place, though the density of conditional mode details makes it slightly harder to parse quickly.

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?

With no output schema, the description bears the burden of explaining behavior and outcomes bel. It covers the modes, status nuances, and points to search_claimed_colors for color claims. It leaves a few minor gaps (exact return fields, how limit applies per mode), but overall gives enough to use the tool 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?

Schema coverage is 63%, and the description adds meaningful semantic value: it explains mode values, gives text examples ('PIZZA', 'stripe'), clarifies statement_type as one of the four statement kinds, and details status restrictions. It does not describe limit or serial_number, but those are straightforward.

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: 'Searches the statements the USPTO records on a trademark' and enumerates the types (disclaimers, descriptions, translations, prior registrations) with concrete examples. It also explicitly differentiates itself by pointing to search_claimed_colors for color claims, distinguishing it from at least one sibling.

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 clear usage context by listing modes, giving question examples, and explaining mode-specific constraints (e.g., status filter semantics and that top_terms cannot produce a registered-only ranking). It names one alternative (search_claimed_colors) but does not provide a full when-to-use vs. not-to-use matrix with the broader sibling set.

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