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

Annotations only declare a destructive write profile, but the description adds the async job model, the polling requirement, single-operation concurrency, the exact refusal semantics, and the multi-system destructive scope. It also implicitly confirms non-idempotency (refusals, re-invocation) consistent with idempotentHint=false.

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 sentences, each load-bearing: scope, async contract, concurrency contract, outage contract. Ordered from what it does to how to drive it, with no restatement of the name or title.

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?

With no output schema, the description supplies the missing return contract (a job_id) and the polling loop needed to consume it, plus the failure modes an agent must handle. Nothing required to invoke and complete this operation is left unstated.

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?

There is one parameter and schema description coverage is 100%, so the schema already documents project_id as a UUID. The description contributes no additional parameter meaning, which matches the baseline of 3 when the schema carries the load.

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 and resource plus the exact blast radius (GitHub repo, K8s deployments, database), which immediately distinguishes it from delete_graph_project, delete_module, and drop_schema_items. An agent can select it without opening any sibling schema.

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 prescribes the follow-up pattern (poll returned job_id with get_job_status) and the two refusal conditions with their remedies: concurrency lockout names the running job and says to wait, and the RationalBloks update window says to retry in a few minutes. This is when/when-not guidance with the alternative tool named.

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