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

Annotations already declare the tool read-only, idempotent, and non-destructive, so the description adds valuable behavioral context: USPTO design vocabulary is literal and narrow, 'stripe' will not resolve to 'Bands, straight' directly, and words like 'swoosh' have no code entry. It also discloses dotted vs packed code formats and mode inference, all beyond what the annotations 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 dense but front-loaded with purpose and concrete examples before moving into caveats and modes. A small amount of redundancy exists because the mode list and mode-inference guidance partly repeat the input schema's mode description, which keeps it from a perfect score.

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 multi-mode tool with no output schema, the description covers the core invocation flow: mode inference, code format flexibility, and the vocabulary limitation that could cause failed searches. It could be more explicit about return shapes for count, top_owners, and list_marks, but the mode names and schema descriptions largely fill that gap.

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 schema covers a large portion of the parameters, but the description adds meaning by explaining the dotted/packed code format, the role of search_codes in resolving shape words to codes, and shorthand semantics for by_serial. It does not add much for limit, match, status, or nice_class, but those are straightforward and already documented in the 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?

The description opens with a specific verb and resource: finding US trademarks by USPTO design code, and immediately distinguishes this from a general trademark search by explaining what design codes are and giving concrete examples. It also enumerates the tool's modes, so an agent can tell exactly what the tool covers.

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 clearly establishes when to use the tool (design-code-based trademark lookup) and how to navigate its internal modes, including the critical rule that a plain shape word must go through search_codes before marks can be counted or listed. It does not explicitly name sibling alternatives or state when not to use this tool, but the intended context is clear.

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