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

Annotations only flag destructiveHint=true; the description goes further by disclosing the concrete downstream consequence (stack definitions that still interpolate it will fail to render on next reconcile) and the irreversibility of the stored value. This is exactly the kind of context structured fields cannot carry.

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 short sentences: the operation, the blast-radius warning with a mitigation, and the irreversibility note. Front-loaded and every sentence earns its place.

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-param destructive mutation with no output schema, the description covers what it does, the risk it creates, how to de-risk (list_stacks), and the non-recoverability. Nothing an agent needs before calling it is missing.

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?

Single required 'name' param with 100% schema coverage, so the schema already documents it. The description implies the identifier is a variable name used for interpolation, adding a small amount of meaning beyond the schema's terse 'Variable name to delete.'

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 (organisation variable) that distinguishes it from siblings like delete_cluster_variable and delete_application_env_secret. An agent can identify the target immediately without opening the 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 names list_stacks as the prerequisite check before deleting, giving a concrete when-to-use precondition. Does not name a dedicated recover/restore alternative, but none is implied to exist.

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