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

With no annotations, the description carries the full burden and does well: it discloses irreversibility ('permanently delete'), the required operator key, and the confirm gate. It stops short of describing what happens to the endpoint's traffic or configuration at deletion time, which is the one remaining behavioral unknown.

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 clauses, zero filler, with the destructive nature and the safer alternative front-loaded. 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 two-parameter mutation with no annotations and no output schema, the description supplies the safety profile, the auth requirement, and the alternative. Only the meaning of endpoint_id and the post-delete state are unaddressed.

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%, so the description must compensate. It does so for confirm ('must be true'), reinforcing the schema's enum, but says nothing about endpoint_id beyond implying it identifies the target. Half the parameters gain meaning, half do not.

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 ('permanently delete a gateway endpoint') plus the domain side ('Seller side'), and it explicitly distinguishes itself from the sibling gateway_pause. An agent can tell this apart from every other gateway_* tool without opening a 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?

Names the alternative (gateway_pause) and the exact condition that selects it ('if you may want it back'), and adds a hard prerequisite ('REQUIRES OPERATOR KEY'). When-to-use, when-not-to-use, and access gating are all present.

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