acme_ask_user

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

With no annotations, the description carries the full burden and does disclose the key behavioral trait: the call may return before an answer exists and must be re-invoked with the event_id, i.e. it is asynchronous rather than blocking indefinitely. It also says where the human answers (dashboard or phone). It omits timeout/duration behavior, whether re-asking with question is allowed, and what a returned answer looks like, so not a 5.

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?

Three tight sentences, front-loaded with the action and motivation before the mechanics. The parentheticals ("which environment, which customer, is this safe") earn their place by making the trigger concrete. Minor informal tone costs it the top score.

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 no output schema and no annotations, the description does most of the needed work: it explains the async wait/poll cycle, where the human replies, and the escalation intent. What is still missing is the shape of a successful return (answer text vs. a status plus event_id) and any guidance on how long to wait before re-calling.

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 100%, so both parameters are already documented in the schema, and the description largely restates them (event_id for continuing a prior question). The extra framing about event_id being "the event_id you were given" reinforces the polling loop but adds no new syntax or constraints. Baseline 3 is appropriate.

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 ("Ask a person on your team a question and wait for their answer") plus the motivation behind it, so an agent knows this is a human-in-the-loop escalation rather than a data lookup. It does not explicitly differentiate itself from the nearest siblings (acme_check_approval, acme_recent_decisions), so it falls short of a 5.

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 clear trigger context with concrete examples of the ambiguity it resolves ("which environment, which customer, is this safe") and explicit polling guidance ("If the answer isn't there yet, call this again with the event_id you were given"). No explicit when-not-to-use or named alternatives against acme_check_approval, which keeps it at 4.

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