Delete a Niche

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

Going well beyond the destructiveHint annotation, the description discloses the full blast radius (keywords, competitors, all dives and diveboxes), irreversibility, that spent dive tokens are NOT refunded, the confirm gate, and the conflict failure mode. Every consequential behavior an agent must surface to a user is covered.

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?

Four sentences, each earning its place: purpose, cascading consequences plus token policy, the confirm gate, and the conflict precondition with resolution. The warning is front-loaded and the structure leads from action to consequence to safeguard to edge case.

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 destructive operation with no output schema, everything needed to call it safely is present: success effects, irreversibility, financial impact, the required confirmation flag, the failure mode, and the resolution path. There is no meaningful gap an agent would need to infer.

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 100%: both nicheId and confirm already carry thorough schema descriptions, including 'Confirm with the user first.' The description's 'Set `confirm: true` only after the user approves' reiterates schema semantics rather than adding new parameter-level meaning, so the high-coverage baseline of 3 applies.

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 states a specific verb and resource ('permanently remove a niche'), making the operation unambiguous. It also inherently differentiates from siblings: it is the destructive counterpart to read-only tools like list_niches and get_niche_keywords, and targets a different resource than delete_rank_radar.

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 explicitly frames when to use it ('a niche the user no longer needs') and states a hard precondition: a niche used by any Rank Radar cannot be deleted. It also names the exact remedy and sibling tool to consult ('delete or archive those rank radars first (`list_rank_radars` with the `nicheId` filter shows them)').

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