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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds the crucial non-obvious traits: the call triggers composition, returns composition errors caused by the removal, may break the running router, and dryRun recomposes without deleting and returns updatedGateway. That is substantive context beyond the annotations.

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?

Front-loaded with purpose, then the composition consequence, then the dryRun safety path, then the inputs — a sensible order. It is slightly repetitive about what deletion does ('deletes from the variant' / dryRun 'deletes nothing'), but every sentence still carries useful signal.

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, composition-triggering mutation with an output schema, the description covers the risk, the safe preview path, the side effects, and the required inputs. Nothing an agent needs to decide whether and how to call it is missing; return values are left to the output schema.

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 coverage is only 25% (just dryRun), yet the description names all three required inputs (graph ID, variant name, subgraph name) and elaborates dryRun's semantics well beyond the schema's one-liner, including that it deletes nothing and reports updatedGateway. It stops short of format hints for graphId or subgraphName.

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+resource (remove a subgraph from a variant), notes the composition side effect, and pins identity against the rover CLI equivalent. It is clearly distinguished from sibling DeleteGraph, which removes an entire graph rather than one subgraph from one variant.

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 explicit operational guidance: perform the removal with dryRun=true first to preview, because a real removal can break the running router. It does not name alternative tools or state when a different approach (e.g. publishing a replacement subgraph) would be preferable, so it stops short of full alternatives coverage.

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