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

The description discloses a crucial behavioral caveat beyond the read-only annotations: the result is an observation signal, NOT confirmed market entry, and sparse sampling can surface long-present sellers. This prevents an agent from over-interpreting results as true new entrants — exactly the kind of semantic-trap context that annotations cannot convey.

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?

Four sentences, roughly 85 words, with zero wasted content: definition, central caveat, sibling distinction, and usage triggers. The most decision-critical information (what 'new' means and its caveat) is front-loaded, and usage guidance comes last. Every sentence 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 an 18-parameter tool with no output schema, the description covers the highest-value semantic ground: the meaning of 'new', the false-positive risk, and routing against the primary sibling. It does not describe return values or pagination, and the 13 undocumented parameters remain a gap, but the conceptual load an agent must grasp before calling is fully addressed.

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 coverage is only 28%, leaving 13 of 18 parameters undocumented. The description supplies the core semantic frame — 'earliest observation in our data falls in the window' — which gives meaning to since_days and earliest_seen_from/to, but it does not compensate for the undocumented filter dimensions (ratings, ASIN counts, FBA share, buybox days). Concept is clarified; parameter-level meaning is mostly still missing.

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 a specific verb ('Find'), a precise resource ('operators we FIRST OBSERVED selling recently'), and pins down exactly what 'new' means: earliest observation in our data falls in the window. It also explicitly distinguishes itself from top_expanding_operators, so an agent can tell them apart without opening the schema.

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?

It names the closest alternative (top_expanding_operators) and states the condition that selects between them: newly observed sellers vs existing operators adding brands. It then gives concrete trigger phrases ('new sellers this month', 'who just started selling', 'newly seen operators') that map natural-language requests directly to this tool.

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