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

Annotations already convey readOnly and non-destructive behavior, so the description's additional burden is lower. It adds valuable behavioral context: results are qualitative evidence (quotes, interpretations) with source attribution and parent trend context, and it explicitly states what the tool is NOT for (raw numbers). This goes beyond the annotations without contradicting them.

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 front-loaded with the most important 'NARRATIVE only' distinction, names a sibling alternative, and closes with a clear usage criterion. It is slightly repetitive (reiterating 'NOT raw numbers' and mentioning search_statistics twice within the description and schema), but each sentence still carries meaningful value and the overall length is reasonable.

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?

There is no output schema, but the description compensates by describing the return characteristics: quotes, interpretations, source attribution, and parent trend context. It also covers graph applicability and when to use alternative tools. It could mention pagination or limit behavior more explicitly, but the essential information for correct selection and invocation is present.

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 documents every parameter thoroughly. The description adds high-level conceptual framing but does not substantially expand on parameter-level semantics beyond what the schema provides. A baseline 3 is appropriate because the schema carries the parameter documentation 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 states a specific verb-resource pair ('search' + 'insights') and clearly defines the scope: narrative-only content such as expert quotes, editorial analysis, and strategic perspectives from named strategists. It explicitly contrasts with raw data tools and names what differentiates it, so an agent can distinguish it from search_statistics without ambiguity.

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 explicitly tells the agent when to use this tool: when needing authoritative voices, strategic framing, or analytical depth. It also names the alternative for hard numbers and market data: search_statistics. It adds the important constraint that it works on ALL graphs, making the decision rule complete.

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