Delete Connection

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

The annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is well-covered. The description adds value by clarifying that deletion also 'drops the stored secret from Kilango's vault,' which is significant behavioral context beyond the annotation — it warns the agent that this is not just removing a config reference but destroying the associated secret. This is genuinely useful supplemental disclosure.

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 a single, compact sentence that front-loads the primary purpose and appends the critical caveat about secret destruction. There is zero waste. Given the simple 2-parameter surface, this length is appropriate.

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 destructive tool with robust annotations (destructiveHint=true) and only one required parameter (provider), the description plus annotations are jointly sufficient. The description notes the vault secret behavior but does not mention effects on dependent resources (e.g., apps using this connection) or the dryRun parameter, which could be relevant. However, for a delete tool with good annotation coverage, this is close to complete.

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 description coverage is 0% (0 paragraphs referencing parameters in the description text); the description mentions 'backend connection' providing context that the provider identifies the connection source, but it does not explicitly describe either the 'provider' or 'dryRun' parameters. However, with only 2 parameters and a reasonably self-explanatory schema (provider = a string with minLength 1, dryRun = boolean defaulting to false), the burden on the description is modest. It partially compensates by framing 'provider' as the target connection, but does not explain the dryRun semantics.

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 uses a specific verb+resource pattern — 'Remove a backend connection' — and adds the important clarifying detail that it drops the stored secret from the vault. This clearly distinguishes it from sibling delete tools (delete_portal, delete_page, delete_content_block) by specifying it targets backend connections specifically. The purpose is unmistakable.

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 provides no explicit guidance on when to use this tool versus alternatives. It does not mention that this is irreversible (beyond the generic destructive annotation), does not reference sibling tools like list_connections or get_connection as prerequisites, and does not state when a user might prefer disconnect vs delete. Given the large sibling family including connect_app, list_connections, and get_connection, this lack of navigation guidance is a gap.

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