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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds substantive behavioral detail beyond them: the deletion is soft, has a 30s propagation window, and leaves attached Functions intact though unreachable. These side-effect and timing disclosures are exactly the kind of context annotations 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?

Two economical sentences: the mutation type is front-loaded, followed immediately by the operational consequences. Every clause carries information; nothing is filler or repetition of the title.

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?

With annotations covering the safety profile and no output schema to explain, the description is nearly sufficient — it covers mutability, timing, and collateral effects on Functions. Only the precise handling of a nonexistent or already-deleted endpoint_id is left unaddressed, a minor gap.

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 endpoint_id parameter, and the description adds no clarification of it. However, the parameter is a single self-evident identifier whose name and required status leave little ambiguity, so the description does not need to compensate heavily.

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 ('Soft-delete a custom endpoint') and qualifies the operation as a soft delete, which separates it cleanly from sibling deleters like delete_function, delete_entity, and delete_field operating on different resources. An agent can identify the target and the mutation type 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?

The description supplies decision-relevant context — routing stops within 30s, attached Functions are untouched but become unreachable — which tells an agent what happens if it proceeds and implicitly signals this is the reversible alternative to a hard removal. It stops short of explicitly naming an alternative (e.g. update_endpoint to merely disable routing) or stating when not to use it.

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