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

Annotations already declare readOnlyHint, non-destructive, and closed-world behavior, but the description adds important operational boundaries: it does not search the knowledge graph, call an LLM, create a lead, or imply a recommendation. It also explains the optional feedback loop and feedbackAction usage, which goes beyond annotation content.

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?

Three sentences, front-loaded with the core read operation and then the necessary boundaries and feedback condition. No filler or repetition.

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?

With an empty parameter schema and an output schema covering returns, the description supplies the operational context an agent needs: scope, non-actions, and feedback routing. Nothing material for correct invocation 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?

Zero parameters are defined, so the rubric baseline is 4. The description appropriately does not invent parameter detail where none exists.

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?

States a specific verb (Read) and resource (machine-readable product catalogue), enumerates the key fields returned, and explicitly states what it is not (no KG search, no LLM call, no lead creation, no product recommendation), which clearly differentiates it from siblings like search_knowledge_graph and submit_business_inquiry.

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?

Provides clear when-to-use context as a read-only discovery call and names explicit exclusions. It also gives a conditional path to submit_agent_feedback only when substantive review finds a specific defect, making the alternative and trigger condition explicit.

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