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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description reinforces and extends this by listing exactly what is destroyed (GitHub repo, K8s deployments, Neo4j DB, credentials). It also discloses async job behavior, concurrency constraints, and refusal conditions—none of which are in the annotations, adding significant transparency.

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, each earning its place: the first states the action and scope, the second covers job polling and concurrency, the third covers the specific RationalBloks refusal. Information is front-loaded with the destructive effect stated first, and there is no filler or redundancy.

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 operation with no output schema, the description covers everything an agent needs: what is deleted, how to track completion (poll job_id), how to handle concurrency refusals, and when to retry. Sibling tool existence is noted but the description makes this tool's behavior self-contained.

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?

The single parameter project_id is fully described in the schema as 'Project ID (UUID)', which is clear and sufficient. The description adds no additional parameter-level information, but with 100% schema coverage, the schema already carries the meaning. Baseline 3 is appropriate.

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?

Description states a specific verb (delete) and resource (graph project) and enumerates what gets removed (GitHub repo, K8s deployments, Neo4j database, credentials). This clearly distinguishes it from siblings like delete_graph_node and delete_graph_relationship, which target different resources.

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?

Provides explicit operational guidance: tells the agent to poll the returned job_id with get_job_status, explains that only one operation runs per project at a time and how to handle refusals, and gives the exact error message for the RationalBloks update condition. This is concrete and actionable, going beyond vague 'use when' advice.

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