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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: the N550-anchored reference range, the single-period snapshot behavior (no forecast), and the caveat that output is not a transaction price. These interpretive constraints help the agent use the result correctly.

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 labeled sections (Purpose, Guidelines, Limits, Ex) make the description highly scannable. Purpose is front-loaded, each sentence earns its place, and the example is the minimal illustration needed. No filler or redundancy with the schema's structured fields.

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 an output schema present, annotations covering the safety profile, and full parameter documentation, the description covers the remaining essential context: anchoring basis, temporal scope, exclusion limits, and a usage example. The only gap is that it doesn't explicitly differentiate from semantically-similar siblings (get_rcb_index, compare_rcb, get_substitution_boundary), leaving that to inference.

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's parameter list ('date (YYYY-MM), region (CN/EU/NA/SEA), grade (P1/P2/P3)') largely restates the schema, but the concrete example 'rCB vs N550 discount CN 2026-09' adds value by demonstrating how a natural-language request maps to the actual parameters, which nudges this to a 4.

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 ('anchored spread between rCB and native carbon black') and defines the deliverable precisely: anchoring ratio rho, discount rate, and price gap per grade/region/period. It positions itself as the quantitative 'how much cheaper is rCB' indicator, which clearly distinguishes it from sibling tools like get_grade_trend (direction) and calculate_saving (custom quotes).

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 Guidelines section explicitly names complementary tools and their conditions: 'pair with get_grade_trend for direction and calculate_saving for custom quotes.' The Limits section adds exclusion guidance ('not transaction price', 'no forecast'), telling the agent when this tool is inappropriate. It stops short of 5 because it doesn't explicitly route the agent away from closely-related siblings like get_rcb_index or compare_rcb.

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