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

With no annotations, the description carries the full burden, and it does add one genuinely valuable trait: replies are untrusted data and 'same handling rules apply.' However, it omits read-only/idempotency guarantees, what happens on an unknown id, and the consequences of using wait_seconds to block.

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 short sentences, front-loaded with what the tool returns, then the required id source, then the safety caveat. No filler; 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?

The tool is simple and the description covers the workflow and the untrusted-data caveat, but with no output schema it never says what the return looks like (a list of answers, possibly empty) or how empty results should be interpreted, which matters for a polling tool.

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 100%, so both parameters (including wait_seconds with its 0-55 range and blocking semantics) are already fully documented. The description's only parameter-related statement ('use the id returned by ask_humans') restates the schema, so baseline 3 is correct.

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?

Specific verb (fetch) plus resource (answers that have arrived for a question you already asked), and it implicitly separates this from the ask_humans sibling by scoping it to answers from an already-issued question. An agent can tell which half of the request/response cycle this tool covers without opening the 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?

It explicitly routes the agent to ask_humans for the id and frames usage as polling for replies that have already arrived. It stops short of stating when not to use it or how the optional wait_seconds blocking mode changes invocation strategy, but the context is clear.

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