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

Goes well beyond the destructiveHint/readOnlyHint annotations: it discloses cascaded deletion of served catalog models (cascaded_model_count), lane fallback to default, irreversibility with the recovery path (re-add with key), and the required permission. These are the exact side effects an agent must know before invoking an irreversible mutation.

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?

One dense paragraph that front-loads the destructive scope, then consequences, then permission – no filler sentences. Minor cost: the CLI twin reference ('the twin of `ankra ai endpoints delete`') is low-value for an API agent and the clauses are packed tightly.

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 no output schema, the description covers target, prerequisites, cascade effects, post-delete fallback behavior, and irreversibility. Nothing an agent needs to call it safely 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?

Schema coverage is 100%, so the baseline is 3; the description adds provenance by stating endpoint_id comes from list_ai_endpoints, which tells the agent where to source the value rather than guessing. It adds no format or validation detail beyond that, so it stops short of a 5.

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 and resource ('Delete one of the organisation's OpenAI-compatible AI endpoints and its stored key') and implicitly separates itself from siblings like delete_ai_model, delete_personal_ai_key, and rename_ai_endpoint by naming the object and its key. An agent can identify the target resource 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?

Gives concrete entry conditions – endpoint_id comes from list_ai_endpoints and the caller needs ai.manage (owners/admins) – which is the operational context needed before calling. It does not explicitly contrast with alternatives such as rename_ai_endpoint or lane-level operations, but for a delete tool the when-to-use case is unambiguous.

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