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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds context beyond this: it mentions 'preview' behavior and 'metadata coverage,' and clarifies that it can intersect color criteria. This gives the agent a clearer sense of the tool's functional scope without contradicting 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 two sentences with no filler. The first sentence front-loads the purpose and key differentiators; the second delivers usage scope and exclusions. Every phrase earns its place, making it compact and efficient.

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 9-parameter tool with no output schema, the description gives a good high-level orientation but omits important invocation details: whether limit affects counts or only previews, how class_match_mode behaves, and the exact return structure. It is sufficient for tool selection but not fully complete for a complex 9-param tool.

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 44% (low), and the description compensates partially by mapping core concepts: 'mark-type' to mark_types, 'standard-character' to standard_characters, 'Nice-class' to nice_classes, 'status' to status_filter, and 'claimed-color criteria' to the color params. However, it does not explain limit, class_match_mode, or interaction nuances, leaving some parameters underspecified.

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 states a specific verb+resource: 'Count and preview USPTO marks by record attributes.' It distinguishes from sibling tools by emphasizing 'rather than owner identity' and explicitly excluding 'color-only counts, rankings, lists, and vocabulary,' which differentiates it from tools like search_by_owner or color-focused searches.

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 explicit when-to-use guidance: 'Use this for drawing type, standard-character, Nice-class, status, and cross-attribute counts.' It also gives exclusions ('color-only counts... are outside its scope'), helping the agent decide against this tool for those needs. However, it does not name specific alternative sibling tools, so it falls short of perfect alternative routing.

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