keychain_secure_connect

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

With no annotations, the description carries full burden. It discloses that the tool checks environment variables first, then opens a localhost input page, and requires two calls. It does not detail safety or failure states, but the secure nature is implied.

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 three sentences, each earning its place: first states purpose, second explains the method, third gives usage steps. No wasted words, front-loaded with key information.

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?

The tool has a moderately complex two-step process. The description explains the flow but lacks details on return values (e.g., what the URL looks like, success/error responses). No output schema is provided, so the description should compensate. It is complete enough for basic use but could be improved.

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 coverage is 100%, so baseline is 3. The description adds meaning by explaining the two-step process and that the first call returns a URL, which is not in the schema. It does not detail each parameter but provides enough context for the required platform parameter.

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's purpose: securely connect a platform credential without exposing the key in chat. It distinguishes from siblings like keychain_connect, keychain_disconnect, etc., by describing a secure two-step method involving environment variable check and secure input page.

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 explains when to use the tool (for secure credential connection) and provides step-by-step usage: call once to get a URL, then call again after user submits. It does not explicitly state when not to use it or mention alternatives like a simpler keychain_connect, but the context of sibling tools fills that gap.

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