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

Annotations cover read-only/idempotent/non-destructive, and the description adds context annotations cannot: this tool never raises a protocol error, it returns {"error": ...} with fix guidance, and retry is safe after correcting input. That error-contract detail is the highest-value thing an agent needs and is not in the structured fields.

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?

Front-loaded with purpose, then semantics, then usage, then error contract — a sensible order with no filler. The inline input and output JSON examples are long but earn their space by demonstrating the asymmetry and empty-string case; the retry sentence is slightly redundant with the idempotent annotation.

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?

Output schema exists so return values need no prose, yet the description still supplies the interpretive layer (which conditions mean ok:false and why shared supplier SKUs are usually benign). With one nested-object parameter, the error contract and retry guidance, nothing an agent needs to call this correctly is missing.

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 coverage is 100% and the schema states 'Store SKU to supplier SKU', so the baseline is 3. The description exceeds that by showing a worked example that reveals the empty-string convention ("STORE-3": "") and the resulting empty_targets semantics, plus the direction of the mapping — meaning the schema alone would not convey.

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?

Opens with a specific verb+resource: 'Find the breaks in a supplier-to-store SKU map'. It goes further by explaining the asymmetry rule (two store SKUs to one supplier SKU is fine; two supplier SKUs to one store SKU is not), which lets an agent distinguish this from the numeric siblings (margin_check, lead_time) without reading the schema.

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?

Explicit 'Use before importing a mapping or handing one to a fulfilment app' plus an explicit exclusion routing to another server ('Not for validating Shopify's CSV columns: that is the shopify server'). Both when and when-not are stated with named alternatives.

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