emu_list_active_calls

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

No annotations are provided, so the description carries the full burden. The word 'List' strongly implies a read-only operation, and the states listed (held, policy-pending) add nuance, but nothing is stated about side effects, mutability, or whether the list is a snapshot. It doesn't contradict any annotations (since none exist), but it would be stronger with an explicit 'does not modify call state' note.

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?

The description is a single sentence that packs purpose, scope, and state enumeration without redundancy or verbosity. It uses precise wording and avoids filler. The structure is immediately parseable.

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 description alone resolves the main ambiguity among siblings: it clarifies it focuses on active calls (unlike general list tools), and names the states. With no annotations provided, this description carries the full contextual load and does so effectively. An agent can decide to use this tool vs emu_list_call_sessions or emu_get_cdr_history based on the phrase 'active or in-progress'.

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?

Both parameters are documented: limit is an integer with description, and state is a string with an explicit enum of allowed values (alerting, connected, policy-pending, held, disconnected). The schema provides full coverage. Missing details like default limit or whether states are mutually exclusive would strengthen it, but the current descriptions are sufficient for an agent to use the parameters correctly.

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 ('Lists active or in-progress telephone call sessions') and enumerates the exact states returned (alerting, connected, policy-pending, held). This distinguishes it sharply from sibling call tools like emu_list_call_sessions (general list) and emu_list_cdr_records (CDR records).

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?

The description implies this is for active/in-progress calls, which differentiates it from historical or all-session listings like emu_list_call_sessions Jewell. It does not explicitly name a sibling or state when not to use it, but the 'active or in-progress' qualifier gives clear contextual guidance.

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