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

Annotations already mark readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds substantial behavioral context: the bitemporal nature (as_of vs detected_at), curated backfill, full sourcing metadata taxonomy, grain-dependent rollup semantics, and access-tier behavior (free preview, Pro/Enterprise full, anonymous none). This greatly enhances transparency beyond 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?

Although the description is fairly long, it is well-structured with clear sections (overview, use cases, filters, access) and avoids redundancy. Every sentence contributes actionable information—scope, examples, alternatives, or constraints—making it appropriately sized for a complex tool with many parameters and access tiers.

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?

With no output schema, the description explains return shapes ('month|quarter returns median/min/max rollups', 'raw returns per-source observations') and mentions source metadata fields. It also covers access tiers, filter semantics, and citation guidance, giving a complete picture for an agent to invoke the tool correctly.

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 0%, so the description must compensate—and it does thoroughly. It lists all seven filters, marks benchmark_type as required, enumerates its allowed values, explains grain semantics (raw vs month/quarter rollups), and clarifies from/to as as_of bounds. This gives effective meaning to every parameter despite the schema's missing descriptions.

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 opens with a specific verb and resource: 'Historical Benchmarks — the bitemporal benchmark-observations ledger...' and enumerates the exact data domains (wafer cost, defect density, CoWoS interposer, etc.). It explicitly differentiates from siblings by naming alternative tools for current point values and other APIs, making the purpose crisp and unambiguous.

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 includes a dedicated 'USE THIS for' block with concrete example queries and a 'DO NOT USE for' block that names specific alternative tools (get_wafer_pricing, get_packaging_costs) and API endpoints (/api/v1/snapshot-series, /api/v1/margin-trends). This offers explicit when-to-use and when-not-to-use guidance, going well beyond a generic statement.

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