company_supplier_scorecard

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal that the scorecard is 'sealed' (implying an immutable/finalized artifact) and that it is built 'from every persisted stock position,' which is useful context. However, it does not clarify the side effects of sealing — whether a persistent record is written, whether the operation is reversible, or whether permissions are required.

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 front-loads the core action but then runs on as a single dense, unbroken sentence mixing the metric enumeration with a parameter note in a trailing parenthetical. The metric list earns its place because it tells the agent what the report covers, but the payload documentation would be clearer as a separate sentence, and the whole thing is structurally unwieldy.

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?

This is a complex tool (7 parameters, 2 required, 0% schema coverage, no annotations), yet the description only covers the output contents and the optional window payload. The required inputs (project_id, bundle_json) are left mysterious, and the behavioral implications of 'sealed' are unaddressed. The output schema covers return values, which excuses that gap, but the input and side-effect gaps are significant.

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 0%, so the description must compensate. It does explain the payload_json contents ('optional window_start, window_end'), which is genuinely helpful. But the two required parameters — project_id and bundle_json — are entirely unexplained; bundle_json in particular is a required string whose meaning is completely opaque, so an agent cannot know what to supply. The now/engine/operation/entity_ref defaults are also undocumented.

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 action and resource ('Build the sealed supplier scorecard') and enumerates exactly what the scorecard contains: purchases, fill rate, on-time receipts, lead time vs policy, price vs standard cost, landed premium, shrinkage/write-downs, single-source exposure, and a supplier grade with its supporting number. This level of specificity clearly distinguishes it from generic siblings like company_vendors, commerce_supplier_evaluation, or company_supply.

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 makes clear what the tool computes and implies when it would be used (when supplier performance metrics over a window are needed from persisted stock positions). However, it never explicitly states when to prefer this tool over alternatives such as commerce_supplier_evaluation, procurement_supplier_evaluation, or commerce_vendor_risk_assessment, and it gives no exclusions or prerequisites.

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