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

Annotations already flag destructiveHint=true, but the description adds substance beyond that: irreversible data loss across five distinct resource types, billing termination, the fact that an unconfirmed call refuses and changes nothing, and that a later redeploy reclaims the URL but not the data. That last point is a non-obvious side effect an agent could not infer.

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 destruction inventory, then the confirmation protocol, then the alternative — a sound ordering with no filler. The opening sentence is long and clause-heavy, which strains readability for such a high-stakes tool, but every clause carries information.

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?

A destructive, irreversible, confirmation-gated operation with an output schema; the description covers blast radius, gating behavior, billing effect, post-deletion URL reuse, and the deferred-teardown alternative. Nothing an agent needs before invoking it safely is missing.

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 100%, so the baseline would be 3, but the description adds the conversational contract for confirm — it must follow an explicit user 'yes' about named losses, and a delete request is not itself that yes — plus the runtime consequence that omitting it causes a no-op refusal. project_id gets no added meaning beyond the schema, which keeps it off 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?

Names a specific verb and resource ('Delete a project for good') and then enumerates exactly what ceases to exist: machine, URL, app files, SQLite database, managed Postgres, and storage bucket contents. That level of specificity makes it unmistakable against siblings like remove_database or schedule_teardown.

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?

Explicitly states the required pre-call protocol (tell the user what is lost, ask, stop, call with confirm: true only after a yes) and names the alternative for a different intent: 'To take a project down later rather than now, use schedule_teardown instead.' Both the when and the when-not are covered.

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