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

Annotations already signal destructiveHint=true, and the description goes far beyond that: it specifies what is destroyed (staged transactions, input rows, provenance tags, import entry), what is preserved (items, branch), the refusal condition, the preview requirement, the retry mechanism, and rollback via version restore. This is exemplary behavioral disclosure for a destructive tool.

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 dense but every sentence earns its place: main effect, preservation semantics, refusal/retry flow, and auth restriction. It is front-loaded with the core action and structured so an agent can quickly extract what gets deleted and what requires confirmation.

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 complex destructive operation with no output schema, the description covers the full invocation lifecycle: preconditions, destructive scope, error/refusal handling, confirmation flag, and rollback path. The only gaps (exact success response shape) are acceptable given the absence of an output schema.

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 the baseline is 3, but the description adds real meaning beyond the schema: it explains that confirm_purge is only used after a PURGE_CONFIRMATION_REQUIRED refusal, and it ties connection_id to the data-source context. This goes beyond merely restating parameter names.

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 opens with a specific verb and resource: 'Disconnect a data source (API connector or file import)' and then details exactly what is dropped, purged, and kept. It clearly distinguishes this tool from sibling delete tools like layerz_delete_branch and layerz_delete_mapping by scoping it to data-source removal.

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 gives clear contextual guidance: it explains what a disconnect entails, when a purge is refused, and when to retry with confirm_purge. It also states an explicit exclusion ('Not available for read-only API keys'), though it does not name alternative tools for cases where a different deletion operation is needed.

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