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

Annotations already mark readOnlyHint=true and destructiveHint=false, but the description adds crucial behavioral context beyond the annotations: this is an observation signal, NOT confirmed market entry, because sparse re-sampling can resurface long-present sellers as 'new.' This caveat is exactly what an agent needs to avoid over-interpreting results.

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 sentences with no wasted words: the core definition and critical caveat are front-loaded, followed by a brief filter note and explicit usage triggers. Every sentence earns its place and the description is appropriately sized for the tool's complexity.

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?

The description adequately defines the primary metric and gives clear usage guidance. However, with 17 parameters, only 35% schema coverage, and no output schema, an agent still lacks enough context about the return format and the semantics of most filter parameters. It is a minimum-viable description with clear 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 only 35% (6 of 17 parameters have descriptions). The description does clarify the core 'newly-OBSERVED sellers' concept, which maps to min_new_sellers and window_days, but it fails to compensate for the many undocumented min/max filters (control scores, churn, total sellers, catalog churn) or brand_contains, limit, and category beyond a passing mention of 'optional category filter.'

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 specific verb and resource ('Find brands that recently gained the most newly-OBSERVED sellers') and precisely defines the metric as first-seen date within the window. It also distinguishes the tool from brand-specific queries by the phrase 'without naming a specific brand,' making its purpose unmistakable.

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 gives explicit usage triggers: 'Use when the user asks...' with multiple concrete phrasings, and includes exclusions: it is an observation signal, not confirmed market entry, and is for category-scoped signals without naming a specific brand. However, it does not name alternative sibling tools, so it stops short of full alternative routing.

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