Start conference

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds nothing about live-call state requirements, whether an existing conference is replaced, or failure modes—real gaps for an operation that mutates an in-progress call.

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?

Two fragments and no filler, so there is nothing to trim. Brevity here reflects under-specification rather than disciplined editing, but the structure is front-loaded and contains no noise.

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 a call-state-mutating CTI action, the description should at minimum describe the live-call precondition and the resulting conference state. It supplies neither, leaving the agent with only the name, endpoint, and schema to work from.

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 mac, line, call_id, and response_format are each documented in the schema; baseline 3 applies. The description contributes no extra meaning—it does not explain that mac identifies the device, line the extension, or call_id the active call to be conferenced.

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 body 'Start conference' is a verbatim restatement of the tool title, and the only other content is an HTTP route (POST /cti/{mac}/start_conference). It gives no indication of what a conference start does at the CTI layer—who is conferenced, on which call—nor how it differs from placetel_cti_complete_conference or placetel_cti_start_transfer.

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?

There is no when-to-use guidance: no statement that an active call is required, no mention of prerequisites such as a valid call_id, and no pointer to the sibling that completes or tears down the conference. The agent must infer the whole workflow from the tool name.

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