get_customer_ai_errors

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

Annotations are absent, so description bears full burden. It indicates a list operation (no mutation), but does not explicitly state read-only behavior, pagination, or authentication needs. The safe read nature is implied by the 'get' prefix.

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?

Two sentences with a clear title-like lead, no redundant info, and front-loaded purpose. Every sentence earns its place.

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?

For a simple filtered list tool, the description covers inputs well and implies output (a list of corrections). No output schema exists, but the tool's simplicity mitigates the gap. Could mention the format of returned corrections.

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 already covers parameters with descriptions and enum values, but the description adds practical usage context: 'pass no parameters to list all' and 'use single keywords only' for query. This adds value beyond the schema.

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 clearly states the tool lists 'Customer AI Corrections' for the CUSTOMER-FACING WhatsApp AI, using a specific verb ('List') and resource ('corrections'). It distinguishes from siblings like get_ai_errors (internal AI) and delete_customer_ai_error.

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 explicit guidance: pass no parameters for all corrections, use category or query for filtering. Does not mention when to prefer this over sibling list tools, but the context of customer-facing vs internal AI is implied by the tool name and description.

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