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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds genuinely new behavioral facts: re-enabling clears the failure count, and writes are never retried automatically. Those two statements materially change how an agent should handle failure and retry, which annotations alone do not convey. It stops short of describing the response or partial-update semantics for omitted fields.

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 sentences, front-loaded with the verb and the mutable field list, with the confirmation requirement and non-retry caveat in descending priority. Slight redundancy with the schema's own description of the confirmed parameter, but nothing is padded.

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, open-world PATCH with no output schema and a nested body object, the definition covers the important unknowns: approval gating, a state side effect (failure count reset), and retry behavior. Missing only the partial-update contract for omitted fields and any hint about the returned representation.

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 only 33%, so the description must carry semantic weight, and it does: it maps 'events' to event_types, 'batch size' to batch_max, 'contact opt-in' to include_contacts, and on/off to is_active, plus it explains the confirmed=true gate. Only the free-text description field is left unaddressed, a minor omission.

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 ("Update webhook") and enumerates exactly which attributes can change: URL, events, batch size, contact opt-in, active status. This clearly separates it from dealmachine_delete_webhooks_id, dealmachine_get_webhooks_id, and the read/rotate/test webhook siblings, though it never names an alternative explicitly.

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?

"Requires user approval and confirmed=true before changes or credit use" gives a real precondition for invoking the tool, which is more than most mutation definitions offer. However it gives no guidance on related workflows, e.g. inspecting current config via dealmachine_get_webhooks_id first or choosing between patching versus recreating a webhook.

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