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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's main value is stating the output composition and filter semantics (min/max hhi gates the analysis; operator filters apply to top_operators). This adds useful behavioral context beyond the annotations, and no contradiction with annotations is present.

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 front-loaded sentences cover purpose/return, use cases, and filter details with no filler. The filter sentence is dense, but every part earns its place.

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 12-parameter tool with no output schema, the description covers the output shape and most filter semantics, but leaves 'limit' undefined, does not state whether at least one of 'asins'/'brand' is required, and narrows marketplace scope to US/UK contrary to the schema. These gaps leave an agent slightly under-informed for actual invocation.

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 description goes beyond terse parameter names by explaining filter grouping, default no-filter behavior, exact/case-insensitive operator matching, and which filters act on top_operators. It does not explain 'limit' and its 'Amazon US/UK' scope is narrower than the marketplace_id schema, but it compensates substantially for the low 42% schema coverage.

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 names the computed metric (HHI) and the exact resource ('a set of ASINs or a brand's catalog'), and states the returned payload (HHI, concentration label, top operators with listing counts). This clearly distinguishes it from sibling operator_* tools focused on brand membership or cross-marketplace presence.

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?

Explicit user intents are given ('how concentrated is this niche', 'who controls this brand's listings', 'is one operator running most of these'), framing it as the private-label fragmentation check. It does not name alternatives or when-not-to-use, so it stops short of a 5.

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