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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description does add useful behavior: case- and accent-insensitive matching, partial-name support, and that richer fields (trend status/score, style tags) appear only 'with a key'. However, it does not disclose pagination behavior beyond limit, or what happens with no matches, leaving real behavioral gaps.

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?

Three dense sentences, front-loaded with the core capability, then return shape, then the empty-query edge case. No filler, no repetition of the title, and each sentence carries information an agent needs.

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 an output schema present, the description needn't explain return structure, yet it still summarizes the fields usefully; auth-tier-dependent fields and the empty-query default are both covered. Remaining gaps are the lack of any routing guidance versus sibling brand tools and no statement about result pagination beyond the limit parameter.

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?

At 60% schema coverage, the description earns above baseline by explaining that query is not just a name but also accepts style words, that matching is case/accent-insensitive and partial, and that empty query has defined sort semantics. It gives light meaning to category and tier via 'optionally within a category or catalog tier', but adds nothing about the agent self-identification object or the anonymous-versus-key limit cap.

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 states a concrete verb and resource — 'Find brands in the index' — and immediately enumerates both matching modes (name substring, style word) plus the optional facets (category, catalog tier). That is far more specific than a restatement of the name, though it never explicitly distinguishes itself from siblings such as similar_brands or trending_brands, so an agent must infer the boundary.

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?

Usage context is clear: use it for name lookup, for style-word discovery ('y2k', 'quiet luxury'), or with an empty query to enumerate all brands by item count. No exclusions or explicit alternative routing are given (nothing says when to prefer similar_brands or trending_brands instead), which keeps it below a 5.

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