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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety and determinism profile is covered. The description adds genuine behavior beyond that: strict refusal of ambiguous input, a `normalized` echo of adopted values, and a mandatory provenance.source_line plus disclaimer that must be passed through to the user. It does not describe printing/rendering behavior or limits such as the 20-row cap, though the schema supplies the cap.

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 purpose sentence is front-loaded and clear, but the body is bilingual duplication plus boilerplate about currency codes, units and dates that is largely irrelevant to a barcode-printing tool with four parameters. Much of the text is recycled shared scaffolding rather than tool-specific value, which dilutes the useful instruction.

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?

An output schema exists, so return values need not be explained, and the annotations cover the safety profile. The definition still covers input discipline, refusal-on-ambiguity, the normalized echo and the provenance/disclaimer obligation, which is enough to call it correctly. The leftover gap is the absence of any routing guidance among the twenty sibling tools.

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% — every parameter (rows, type, paper, startCell) carries its own bilingual description and both enums are enumerated in the schema. The description adds only general input-formatting rules (decimal strings, date forms, no currency symbols) that apply to figures and dates, which this tool's own parameters barely use. Baseline 3 is correct when the schema does the heavy lifting.

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 the concrete resource and output (EAN-13, UPC-A, FNSKU barcodes printed on A4 or label stock), which tells an agent exactly what the tool produces and distinguishes it from calculation siblings like amazon-fees or cbm. It stops short of naming any sibling tool or comparing against one, so it lands at 4 rather than 5.

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 gives real input-discipline guidance: quote exact decimal strings, never invent a number or date the user did not supply, ask for required values and omit optional ones. What it lacks is any when-to-use routing — no statement about when label generation applies versus the pricing/conversion siblings, and no prerequisites such as print setup.

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