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

With no annotations, the description carries the behavioral burden and largely succeeds: it discloses asynchronous follow-up via check_answer, expected latency in Central Time business hours, and rate limiting with a batching mitigation. Minor gaps remain around failure handling or what happens if no human can answer, but the core behavior is clear.

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, sentences each earning their place: what to ask, latency plus return mechanism, and rate-limit guidance. The use cases are front-loaded and 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?

For a five-parameter, no-annotation, no-output-schema async tool, the description is close to sufficient: it covers question scope, async polling mechanism, timing, and rate limiting. It could clarify behavior for edge cases or how optional parameters affect routing, but nothing essental for a correct call is missing.

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 coverage is 60%, and the description adds meaning mainly to the question parameter by illustrating what counts as a human-answerable question. It does not elaborate on city or agent, but those are self-explanatory and the schema already describes contact and apartments. The description provides acceptable but not comprehensive parameter value.

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?

The description names a precise verb-object pair ('Ask a question... a human locator'), scopes it to 'a question only a human can answer,' and gives concrete examples like current specials, real availability, and lease flexibility. It also differentiates itself from siblings by noting it returns a question_id to poll with check_answer.

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?

It provides a clear selection criterion ('only a human can answer') with examples that distinguish it from search_apartments, plus operational guidance about business hours and batching under rate limits. It does not explicitly name all alternatives or state when not to use the tool, but the context is strong.

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