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

With no annotations, the description fully discloses the tool's sensitivity ('high-privilege credential; do not log or expose it'), its refusal of production connections, the prerequisite call to get_connected_accounts, an edge case about older connections, and cost in tokens. No contradiction with annotations exists.

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 well-structured and front-loaded: it begins with the primary purpose, then a bolded security warning, then scope, prerequisite, edge case, and cost. Each sentence serves a purpose, and no filler is present.

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 that an output schema exists, the description does not need to explain return values. It covers purpose, usage, exclusions, prerequisites, a specific failure/edge case, and cost, making it complete for a developer-facing credential retrieval 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 already provides 100% coverage for the single optional parameter with a clear description ('Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account.'). The tool description paraphrases the same information without adding new parameter-specific details, so it adds no meaningful semantic 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 returns the Publishable Key and Secret Key for a connected development Clerk instance, with the specific purpose of configuring a local app environment (including explicit env var names). This is a specific verb ('Return'), a specific resource, and distinguishes it from siblings like get_api_key by scoping to development instances and returning both keys.

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?

It provides explicit when-to-use context: 'Development only. Production connections are refused.' and requires 'Call clerk.get_connected_accounts first.' It also explains default behavior when clerk_instance_id is omitted. However, it does not explicitly name alternative tools for production key retrieval, so it stops short of full alternative guidance.

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