Pipes Drop Pipe

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so the safety profile is covered. The description adds only 'Requires confirmation'; it does not disclose irreversibility (Snowflake pipes have no undrop in this toolset), that load history/pending files may be lost, or that privileges are needed — meaningful gaps for a drop operation.

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?

Two short sentences, front-loaded with the action, with no filler. Brevity is appropriate, though it comes at the cost of the prerequisites an agent needs for a destructive call.

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?

An output schema exists, so return values needn't be explained, but for a destructive, non-idempotent, open-world tool the description is thin: it omits whether the pipe must be suspended, whether the drop is recoverable, and how the confirm flag interacts with defaults. The 75% schema coverage leaves the confirm parameter effectively undocumented in both places.

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 75%, with pipe_name/database/schema_name documented by the schema itself. The phrase 'Requires confirmation' gives the only semantic hint for the undocumented confirm parameter, but it never names the parameter or explains that default false likely refuses the drop — so the added value is suggestive rather than explicit.

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?

States a specific verb and resource ('Drop a Snowpipe'), which cleanly separates it from the other pipes_* siblings (list, describe, create, get_status). It does not name what it is *not* or clarify scope (e.g., whether cascade/dependency handling occurs), but the operation itself is 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?

'Requires confirmation' is the only usage signal, and it usefully implies the confirm flag must be supplied with intent to act. There is no explicit guidance on prerequisites such as ownership, suspending the pipe first, or what happens to already-staged files, which an agent would need before calling a destructive drop.

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