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

Annotations already mark the operation as read-only and non-destructive, and the description adds useful behavioral context: results link back to expert trends, 'HARD NUMBERS only' restricts the output, and the tool works across all graphs. It also advises searching multiple graphs for better coverage. There is no contradiction with the annotations.

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?

The description is succinct yet information-dense. It front-loads the core purpose ('HARD NUMBERS only'), immediately follows with usage guidance, and closes with a short alternative and scope clarification. No filler exists; each sentence contributes to tool selection and successful invocation.

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 search tool with six parameters, required graph_id and query, and no output schema, the description provides enough complete context: it defines the result content, explains the linking behavior to expert trends, states graph scope, and gives a clear selection heuristic. It also mentions coverage across multiple graphs, which helps an agent plan calls.

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 schema already explains all parameters. The description adds little new detail about individual parameters, though it does emphasize that graph_id can target all graphs and recommends searching multiple graphs. This is a baseline score because the schema carries the main parameter burden.

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 action and resource ('search statistics'), states 'HARD NUMBERS only', and enumerates the content type (figures, market sizes, growth rates). It clearly distinguishes itself from search_insights, which handles quotes and narrative, making it easy for an agent to select the right tool.

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 usage conditions are given: 'Use when a question asks for a number or statistic — try this BEFORE supplemental data tools.' It also names the alternative search_insights and the conditions under which to use it (expert quotes, editorial analysis, narrative interpretation), leaving no ambiguity about when to choose each tool.

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