recommend_nice_classesRecommend Nice trademark classes based on a business description. Returns the most relevant classes with confidence scores and explanations.
| Name | Required | Description | Default |
|---|---|---|---|
| industry | No | Optional industry category for context | |
| business_description | Yes | Detailed description of the business, products, or services (minimum 50 characters). Pass the full user description, do not summarize. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds that it returns 'the most relevant classes with confidence scores and explanations,' but it does not disclose how relevance is determined or any other behavioral traits beyond the output format. With annotations covering safety, a 3 is appropriate.
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?
Two sentences, front-loaded with the core action, and no filler. Every word earns its place, making this a model of concise description.
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 2 well-documented parameters and no output schema, the description sufficiently explains the input (business description) and output (relevant classes with confidence scores and explanations). It could mention how many classes are returned or how the optional industry parameter affects results, but these are nice-to-have rather than gaps.
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 description coverage is 100%, with both parameters (business_description and industry) fully described, including a minLength and instruction to pass the full user description. The description itself adds no extra parameter-level detail, so it matches the baseline expected when schema carries the load.
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 ('Recommend') and resource ('Nice trademark classes'), and clearly ties it to an input condition ('based on a business description'). This distinguishes it from sibling tools like get_nice_classes (which likely retrieves class data) and suggest_gs_descriptions (which suggests goods/services descriptions).
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 implies when to use this tool: when the user has a business description and needs relevant trademark classes. However, it does not explicitly mention alternatives or exclusions, so it stops short of a full guidance score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly defined scopes, but several search/count tools overlap (search_trademarks, phonetic_search, run_knockout_search, get_similar_marks) and owner/firm analytics tools have similar boundaries. Descriptions help differentiate them, but the large set increases the chance of misselection.
All tool names follow a consistent lowercase snake_case verb_noun pattern (get_, search_, run_, analyze_, etc.). The only minor deviation is web_research, which is noun_verb, but it remains perfectly readable and consistent with the overall style.
61 tools is extreme for any server, far exceeding the 50+ threshold. Even for a comprehensive trademark platform, this number overwhelms agents with selection complexity and makes the toolset difficult to navigate.
Several tools launch asynchronous processes and instruct users to call status tools (get_prosecution_history_status, get_ttab_proceeding_analysis_status, get_office_action_research_status) that are not present in the toolset. Additionally, search_trademarks and phonetic_search reference list_marks_containing_term, which is also missing. These critical gaps cause agent failures when following the described workflows.