delete_stanza

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

With no annotations present, the description carries the full behavioral burden. It discloses that the tool previews by default, can delete directly when confirm=true, and requires an expected preview value for confirmation. It also communicates a safety stance about explicit user intent. It does not mention irreversibility, cascading deletion of links, or permission requirements, but the core destructive behavior is reasonably surfaced.

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?

Three short sentences, each earning its place: the operation, the preview/confirm behavior, and the explicit user-consent rule. The most important safety guidance is front-loaded after the one-line purpose, and there is no filler.

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 output schema exists, so return-value documentation is not the description's burden. The description provides strong safety and workflow context for a destructive operation, but it leaves the 'why' parameter and the precise contract of 'expected' under-specified. For a simple 4-parameter tool, this is close to complete but has a real gap.

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%, so the description must compensate. It adds meaning to confirm by explaining it bypasses preview, and to expected by tying it to the preview result. However, the required 'why' parameter is not explained at all, and the exact expected-value mechanics remain somewhat cryptic. This is partial compensation, not full.

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 begins with a specific verb and resource: 'Delete a stanza,' which clearly distinguishes it from sibling tools like create_stanza, update_stanza, list_stanzas, and get_stanza. It also adds the conditional preview/confirm behavior, making the tool's core function 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 gives explicit when-not-to-call guidance: 'Do not call unless the user explicitly asked to delete this stanza. Findings are not a reason to delete.' This is a strong gate that prevents misuse of a destructive tool. It also signals a preview-first workflow unless confirmation is provided.

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