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

Beyond the annotations (destructiveHint=true), it discloses that this is a soft delete, that data is not permanently removed, that Apollo support can restore the graph, that all variants stop serving, and that it returns null on success. That is exactly the behavioral context an agent needs before committing a destructive call.

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 short sentences with the destructive scope and the confirm-first warning front-loaded, so the highest-risk information lands first. The trailing 'Provide the graph ID' restates the required parameter already implied earlier, which is mild redundancy but not harmful.

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 single-parameter destructive tool with an output schema (so return values need not be spelled out), the description covers reversibility, blast radius, confirmation, and the null result. The only real omission is any contrast with the sibling DeleteSubgraph tool.

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 0% for the single graphId parameter, so the description has to carry the meaning. It says 'Provide the graph ID' and implies an opaque identifier by telling the agent to confirm it with the user, but adds no format, naming, or lookup guidance worth more than a baseline.

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 verb and resource ('Delete a graph') and defines the blast radius ('Every variant of the graph stops serving'), which is clearer than the bare tool name. However, it never distinguishes itself from the sibling DeleteSubgraph, so an agent must infer which deletion target it wants.

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?

It gives one concrete precondition ('confirm the graph ID with the user before you call this'), which is genuinely useful for a destructive operation. It offers no when-not guidance and does not name DeleteSubgraph as the alternative for subgraph-level deletion, so routing between siblings is left to inference.

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