create_instance

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 effectively discloses key behaviors: free tier provisions in ~30 seconds, paid tiers return a Stripe checkout URL, and lists available tiers with sizes and pricing. This goes beyond a simple 'create' statement and gives the agent actionable information about the tool's behavior. However, it could also mention that instance creation is asynchronous for paid tiers (only URL returned) and does not detail the response object for free tier.

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 extremely concise, consisting of two sentences and a bullet-like list. It front-loads the purpose and immediately follows with key behavioral details and tier options. Every sentence adds value without redundancy. The structure is streamlined and easy to parse, making it efficient for an AI agent to understand quickly.

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 (2 required parameters, no output schema), the description provides most necessary context: it covers the purpose, tier options, pricing, provisioning time differences, and hints at the return type (checkout URL for paid). However, it does not explicitly state the return format for the free tier (likely an instance ID or success indication), which would complete the picture. The absence of an output schema makes this gap noticeable but not critical for a straightforward creation tool.

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% description coverage, but the description adds substantial value beyond the schema. For the 'tier' parameter, the description enriches the enum values with specific sizes (e.g., '25 MB', '200 MB'), pricing (€19/mo), and special features (e.g., 'Dragonfly + Semantic Cache' for speed). It also provides usage advice ('Start with "free" for testing.'). For the 'name' parameter, the schema already states uniqueness, but the description reinforces it with a length constraint ('min 3 chars'). This ensures the agent can make informed decisions about parameter values.

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 action and resource: 'Create a new managed Valkey/Redis cache instance on cachly.dev.' It uses a specific verb ('Create') and specifies the exact resource ('Valkey/Redis cache instance'), making the tool's purpose unmistakable. While not explicitly distinguishing from siblings, the context shows no other instance-creation tool exists, so the purpose is fully unambiguous.

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 implies usage for creating a cache instance but lacks explicit guidance on when to use this tool versus alternatives. It mentions that the free tier is suitable for testing, which provides some context, but does not state when not to use it (e.g., when an instance already exists) or suggest alternatives like update or delete tools. The guidance is implicit rather than explicit.

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