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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive). The description adds substantial behavioral context beyond that: the blocking/hold semantics, the ended=true/false return contract, the branchable outcome enum values, and the timeout default/cap tied to the nginx proxy_read_timeout limit. For a long-polling tool with no output schema, this is exactly the disclosure needed.

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?

Front-loaded with the core blocking behavior, then return semantics, then outcome values, then timeout specifics. Efficient and well-ordered, though the timeout default/cap is restated in both the description and the schema, a minor redundancy.

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, the description fully carries the return contract (ended flag, final state, outcome enum) and the timeout/expiry behavior. An agent has everything needed to call and branch on results correctly.

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 the schema already documents call_id, in_workspace, and timeout_seconds. The description reinforces the timeout default/cap and the re-issue pattern, but adds little else. 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 precise verb+resource: 'Block until a voice call ends (status changes from active) or timeout elapses.' This clearly distinguishes it from siblings like calls_list_active, calls_hangup, and calls_make, which an agent can rule out 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?

Explains when the tool applies (wait for call completion) and what to do on timeout ('re-issue to keep waiting'). It gives clear operational context but does not explicitly contrast with an alternative like polling calls_list_active or using calls_get, so it stops short of full when/when-not guidance.

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