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

With no annotations, the description carries the full burden. It extensively details what the tool returns: GMROI, turnover, DIO, dead stock %, carrying cost leakage, composite score, benchmarks, risk flags, diagnosis, and recommended actions. This gives the agent a clear picture of the tool's behavior and outputs, though it does not explicitly state side effects (e.g., whether it is read-only) or data access requirements, which are assumed for a calculation tool.

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 a single sentence that is front-loaded with the core action and then enumerates outputs. It is efficient, with no fluff, but it is dense and might be easier to parse if broken into shorter sentences. Every phrase adds value, but the overall structure is a long run-on, slightly harming readability.

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 lists numerous output dimensions, giving substantial coverage of what the tool returns, but leaves gaps: it does not explain how the composite score is calculated, what benchmark sources are used, or how to interpret the risk flags. It also omits usage context (when to choose this over quick_inventory_diagnosis) and parameter semantics. Given the tool's complexity (8 params, no output schema), the description is moderately complete but not fully self-sufficient.

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?

The input schema has 8 required parameters with 0% schema_description_coverage (no parameter descriptions in the schema). The tool description also fails to explain any parameters—it only lists outputs. Since the description does not compensate for the lack of parameter semantics, the agent must rely solely on names, types, and constraints, which are insufficient for understanding how each input affects the calculation.

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 states the tool's function: 'Calculates a comprehensive inventory health score for a Shopify merchant.' It specifies a concrete verb ('calculates'), a resource ('inventory health score'), and lists detailed outputs (GMROI, turnover, DIO, dead stock exposure, etc.), distinguishing it from siblings like quick_inventory_diagnosis by emphasizing 'comprehensive' and the extensive result set.

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 implies the tool is for in-depth health analysis but does not explicitly state when to use it versus alternatives. It provides no references to sibling tools (landed_cost_calculator, quick_inventory_diagnosis) or exclusions. The word 'comprehensive' hints at a use case, but concrete guidance is missing, qualifying as implied usage rather than explicit directives.

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