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

Annotations already indicate destructive and non-idempotent behavior, but the description adds crucial details: it runs as a job, requires polling, enforces single-operation-per-project, and may be refused during external updates. These behaviors are not in annotations, so the description adds significant value.

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?

Three sentences convey all necessary information without excessive verbosity. The main action and scope are front-loaded, followed by polling and refusal handling. Slightly dense but well-structured for a complex destructive operation.

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 async tool with no output schema, the description covers all required operational details: polling mechanism, conflict handling, and retry logic. An agent has everything needed to invoke and manage the job correctly.

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%, with project_id described as 'Project ID (UUID)'. The description does not add anything beyond this, so it meets the baseline but does not exceed it.

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 clear verb ('Delete') and resource ('project'), and enumerates exactly what deletion entails (GitHub repo, K8s deployments, database). This distinguishes it from related tools like delete_graph_project. The purpose is unambiguous.

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 instructs the user to poll the returned job_id with get_job_status, and explains refusal conditions (concurrent operation or RationalBloks update) with next steps. This provides complete usage guidance for a complex asynchronous operation.

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