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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's safe. The description adds context about the scope (USPTO/TTAB codes and small tables) but doesn't elaborate on return format, pagination behavior beyond the schemas, or any limitations. It does not contradict annotations.

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 sentence that is concise and information-dense. It front-loads the purpose (look up reference codes) and then lists example categories. No filler words. It earns a high score for being efficiently structured, though it could be slightly more explicit about usage exclusions.

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?

Given that the tool has 5 parameters with full schema coverage, no output schema, and no nested objects, the description covers the core purpose. It lacks details on which specific reference types are included (though the enum covers that) and doesn't mention edge cases like when to use code vs query. However, for a lookup tool, the schema plus annotations suffice for an agent to call it correctly. Minor gaps: no mention of return format or error cases.

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%, meaning all five parameters are documented in the schema. The description mentions 'look up codes and small lookup tables' which aligns with the reference_type enum, but it doesn't add meaningful semantic detail beyond the schema. For example, it doesn't explain the relationship between code and query, or the after_code pagination cursor. Baseline 3 is appropriate since schema covers semantics fully.

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 identifies the tool's purpose: looking up USPTO or TTAB reference codes and small lookup tables. It uses a specific verb ('look up') and lists the resource categories (status codes, statement types, legal entity types, Nice classes, design codes, TTAB codes). It distinguishes itself from siblings like get_nice_classes and get_event_code_reference by covering broader reference tables, though it doesn't explicitly name them.

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 implies when to use: when needing to look up reference codes or enum-like values. However, it does not explicitly mention when to use alternatives like get_nice_classes or get_event_code_reference, nor does it state when not to use this tool. The context suggests it's for small lookup tables, but the distinction from similar tools is not explicit.

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