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

Annotations already mark it destructive/non-read-only, but the description adds substantial context the annotations do not: cascade deletion of environments and volumes with data, ordered deletion ('Default last'), async return semantics ('removed or removing'), partial-failure behavior for unresponsive servers, and the possibility of a human approval gate. This is rich beyond the structured hints.

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 short sentences, with the primary action front-loaded. The distributed-server sentence is dense and slightly cryptic, but no sentence is 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?

For a destructive, high-consequence operation with no output schema and very low parameter documentation, the description covers the blast radius and async/approval flow well but leaves half the parameters opaque. Adequate but with clear gaps given the tool's complexity.

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 only 17% (just the approval param) across 6 parameters, so the description must carry the burden and largely does not. It gestures at approval ('may stop to ask a human') and at data loss implicitly, but version, every_copy, wait_seconds, and accept_volume_loss are left unexplained in both schema and description.

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+resource ('Delete a Project') and precisely defines the cascade scope (every Environment, Volume, and their data), which distinguishes it from the narrower environment_remove/volume_remove siblings. It stops short of explicitly naming those siblings, so an agent must infer the distinction from scope alone.

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 never states when to choose this tool over project_rename, environment_remove, or volume_remove, nor any prerequisites or exclusions. The cascade and approval notes are behavioral, not usage-routing guidance.

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