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

Goes well beyond the annotations. Annotations only declare destructive/non-idempotent; the description discloses exactly what is destroyed, that execution is asynchronous with a job_id to poll, the single-operation-per-project lock and its refusal semantics (naming the running job), and a transient refusal during platform updates.

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 dense sentences, each carrying distinct operational value (scope of deletion, async polling, concurrency/update-window retries). Front-loaded with the destructive scope before the coordination mechanics, with no 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, one-parameter tool with no output schema, everything an agent needs is present: what gets removed, that the result is a job_id, how to poll it, and how refusals behave. No important gap remains.

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?

Only one parameter (project_id) with 100% schema description coverage, so the schema already documents it fully. The description adds no format or constraint detail about project_id beyond what the schema provides, so the baseline 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?

States a specific verb (Delete) and resource (graph project), and immediately enumerates the downstream assets removed (GitHub repo, K8s deployments, Neo4j database, credentials). This scope makes it readily distinguishable from siblings like delete_project or rollback_graph_project.

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?

Gives strong operational guidance: it runs as a job and must be polled via get_job_status, one operation per project at a time, and retry behavior during RationalBloks updates. It does not explicitly contrast itself against sibling alternatives such as delete_project or rollback_graph_project, but the when/how guidance is concrete.

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