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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that gaps are computed demand-first in raw text-embedding space (not fixed categories), defines what constitutes a gap (clusters far from paid providers), explicitly mentions that request counts are not buyer counts, and honestly notes that results are sparse when query volume is low and sharpen over time. This is exemplary transparency about limitations and computational methodology.

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?

Although the description is lengthy, every sentence contributes essential information: purpose, interpretation caveats, computational approach, definition of gaps, return contents, and behavior over time. It is front-loaded with the core purpose and structured logically. Minor redundancy (repeating 'not buyer counts' in different forms) slightly reduces efficiency, but overall it is well-organized and appropriately detailed 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 covers all critical aspects for correct invocation: it states the purpose, the input (no required args, limit cap), the output (demand phrasing, demand_mass, nearest_paid_similarity, closest provider, demand_queries, paid_supply counts), limitations (low volume yields few gaps), and usage precautions. There is no output schema, so the description adequately explains return values. For a tool of this complexity, the description is remarkably complete.

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 100%, so the baseline is 3. The description clarifies that no arguments are required ({}), and mentions the limit caps the list, which adds a small amount of guidance beyond the schema. However, it does not elaborate on the 'rank' enum or 'sector' beyond what the schema already explains, so it does not exceed the baseline significantly.

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 identifies the specific verb ('Inspect') and resource ('query clusters with weak coverage among indexed paid providers'), and immediately differentiates it from buyer-count analysis ('research leads, not buyer counts'). It also distinguishes itself from sibling tools like demand_signals or rank_providers by focusing on gaps relative to paid providers. This makes the purpose unambiguous and distinct.

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 strong usage context: it says to use it for research leads rather than inferring buyer counts, and warns that gaps in the index do not prove gaps in the wider market. While it does not explicitly name alternative tools, it clearly advises on interpretation and when the tool is appropriate (i.e., for lead research with caution). This is more than adequate guidance.

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