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

Goes well beyond the destructiveHint=true / readOnlyHint=false annotations: it states the operation is IRREVERSIBLE, that there is no restore point in the product, that nothing can read an earlier revision back, and it explains the opaque-id hazard that motivates confirmName. That is exactly the operational context an agent needs before a destructive call.

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?

Front-loaded with the destructive fact and scope before any rationale, and every sentence carries content. The confirmName rationale runs long ('That is not ceremony —') and the closing sentence on superseded projects is a slight detour, so it is efficient rather than tight.

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 tool with no output schema and only two params, it covers irreversibility, confirmation requirements, and the failure mode of stale ids. It does not mention auth/permission requirements or whether a project must be empty or unpublished before deletion, which would round it out.

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 50% (projectId is undocumented). The description compensates for confirmName by specifying exact-match semantics and the reason it exists — ids are opaque and a stale list may point at a different project — which is meaningfully more than the schema's 'exactly as uichemy_list_projects shows it.' projectId is left to inference, keeping it from a 5.

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 (delete) and resource (a whole project) and immediately scopes the blast radius: 'its sitemap, its sections and everything written into them.' This is clearly distinguishable from the sibling partial removals (remove_page, remove_section, delete_variant), which delete narrower things.

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?

Provides a use case in the closing sentence — superseded projects accumulate with no way to remove them except the browser — which tells the agent when this tool is the right lever. It does not explicitly name an alternative or state exclusions (e.g. it never says 'use remove_section for partial cleanup'), so it stops short of full routing guidance.

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