get_instance

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

No annotations are provided, so the description carries the full transparency burden. It declares 'Read-only' and explains error behavior, which is adequate for a simple read operation. However, it could mention the response format or that metadata includes all listed fields, though the description already implies that.

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 is compact (four sentences) and front-loaded with the core purpose. Every sentence adds value: what it returns, read-only nature, error handling, and alternatives. No fluff 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?

Given the tool's simplicity (single parameter, no output schema), the description covers all needed information: purpose, parameter usage, error scenarios, and differentiation from related tools. An agent can confidently invoke it without additional context.

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?

The input schema has 100% coverage with a clear description for instance_id ('UUID of the instance (from list_instances)'). The description does not add new semantic meaning beyond that, but it reinforces the parameter's role by referencing list_instances. Baseline 3 is appropriate given the schema is self-sufficient.

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 retrieves full metadata for a specific cache instance and lists the attributes (name, tier, status, etc.). It also distinguishes from siblings like list_instances (discovery) and get_connection_string (URL only), providing specific verb+resource differentiation.

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 guidance is given: 'Call list_instances first to discover valid UUIDs' and 'Use get_connection_string instead if you only need the redis:// URL'. It also specifies error conditions ('returns an error if not found or belongs to another account'), leaving no ambiguity about when to use this tool.

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