contact_operator

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

Annotations provide only destructiveHint=false and a title, so the description must carry the behavioral burden — and it does: it discloses that a ticket is filed and an operator notified, the dedupe contract, rate limits with retryAfter, 401 rejection for admin-terminated accounts, the ops-email throttle bypass, and that replies arrive as a message on this account (with no separate reply-fetch call). Nothing contradict the annotations.

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?

Long (roughly 350 words), but the purpose is front-loaded in the first sentence, which is exactly where agents make route decisions. The dedupe section is the one place that runs, passing a few sentences to land 'text match, not intent match' — it could be tightened. Still, every sentence carries non-redundant behavioral detail; there is no filler.

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?

Even with no output schema, the description supplies the return shape ({ ticketId, note, deduplicated }), the dedupe idempotency behavior, the rate-limit response shape (429 with state that provides retryAfter), the auth-edge exception, the account-state compatibility, and the reply-delivery mechanism. For an agent need to call this correctly, nothing is left unstated.

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 fully owns parameter semantics. It explains body as the message text (1-2000 chars), urgency as the 'normal' vs 'needs_human' values with default, and, crucially, the escape semantics of 'needs_human' always filing a new ticket even within the dedupe window. The explanation also reveals that both body and urgency together form the dedupe key, which is well beyond what the schema reveals.

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?

Opens with a precise verb+resource, 'Reach a human operator', and immediately narrows the purpose as the catch-all for what list_messages and infrastructure_status cannot answer, with concrete example scenarios (billing, stuck vendor, account-level ask). It is instantly distinguishable from the sibling set even without opening any 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 alternatives (list_messages / infrastructure_status) and states the conditions that route to this tool: issues those tools cannot answer, and specifically the 'why is my account suspended?' case. It also gives clear when-not-to-send guidance: the text-match dedupe means a genuine new ask with identical wording must be rewritten or escalated.

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