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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description adds value by specifying the nuanced behavior: it is a soft-delete, revisions are retained, and open jobs block the operation. This goes beyond the simple destructive flag and informs the agent about consequences and prerequisites.

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?

Two concise sentences front-load the action and its key effects, followed by the critical prerequisite. Every clause carries information without redundancy or 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 2-parameter destructive tool with an output schema and annotations, the description covers the main behavioral constraints (soft-delete, blocking condition, cancellation path). It does not mention auth or rate limits, but those are typically outside description scope; the essential call-time knowledge is present.

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% and both parameters (projectId, confirm) are already documented in the schema. The description does not add additional parameter-level meaning, so the 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 action ('Soft-delete'), the resource ('a project'), and the behavioral effect ('hidden from listings; revisions retained'). This clearly distinguishes it from other delete tools like deployment_delete or integrations_delete, and clarifies it is not a permanent deletion.

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 an explicit precondition ('Open jobs block deletion') and directs the agent to a sibling tool for the required workaround ('cancel them first with job_cancel'). It implies when to use it (when no open jobs exist) and when not to, with a concrete alternative.

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