Recover Supplier Directory, Real Lead Times & MOQs from Stocky PO CSV

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description focuses on adding value: it discloses that outputs are inferred/derived (lead times computed from Created-to-Received timestamps, pack sizes 'GCD-inferred', min spend 'historical') rather than authoritative, which is important caveat context. It stops short of stating how missing or malformed data is handled.

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?

A single dense sentence that front-loads the motivating problem (Stocky shutdown, no Supplier Directory export) before the payload. Every clause carries distinct information about an output artifact; slightly long, but nothing is filler.

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?

Two optional parameters, full schema coverage, and rich annotations mean little else is needed. With no output schema, the description does the heavy lifting by enumerating the reconstructed fields and the ready-to-use supplier_rules JSON, which is exactly what an agent needs to decide whether to call it and how to chain it.

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%, so the baseline is 3; the description adds the non-obvious semantic that the two parameters are alternatives ('or pass demo_mode: true'), i.e. either a real CSV or the fixture, which the schema alone doesn't convey. It does not clarify the 5MB limit or what a partial/truncated CSV yields, keeping it off a 5.

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?

Specific verb+resource: 'reconstructs every supplier profile' from a Stocky PO CSV, and it enumerates exactly which derived values (lead-time mean/stdev, latest unit cost, GCD carton packs, min PO spend, supplier_rules). It differentiates from the closest sibling by naming build_supplier_purchase_orders as the downstream consumer, though calculate_replenishment_plan and reconcile_po_three_way_match are never positioned relative to it.

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?

Clear context for invocation: paste a historical Stocky PO CSV, or use demo_mode to test against the built-in fixture. The Stocky shutdown framing makes the 'when' obvious. No explicit exclusions or error-condition guidance (e.g. malformed CSV, oversized file), but the trigger condition is unambiguous.

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