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

With no annotations, the description carries the disclosure burden. It reveals that the service stores a pointer rather than full media ('Temsor keeps a pointer') and that STT processing only occurs during active calls, which is useful side-effect information. It omits other behavioral details such as persistence/retention, idempotency, or what happens to previously notified chunks.

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 definition is short and front-loaded, with the core operation in the first clause and key preference/behavior in the following sentences. The parenthetical 'idle $0' is cryptic and unexplained, which slightly reduces clarity, but 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 tool with no annotations and no output schema, the description is too sparse. It fails to define t_ms and pbx_id semantics, doesn't explain what response or acknowledgement to expect, and leaves 'idle $0' ambiguous, so an agent cannot fully determine correct invocation.

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?

Only uri and bytes_b64 have schema descriptions; context signals put schema coverage at 40%. The description reinforces that a customer URI is preferred and that bytes_b64 is a demo fallback, but t_ms and pbx_id are left completely unexplained, and call_id is only implied. Low schema coverage means the description needed to compensate for these gaps and did not.

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 uses a specific verb ('Notify') and names the resource ('optional audio chunk / customer URI') for a live or archived PBX call. It does not explicitly distinguish itself from PBX siblings like pbx_events or pbx_register, but the audio-focused resource makes the scope reasonably clear.

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 states the preferred input mode ('Prefer customer storage URI') and a key temporal constraint ('STT only while a call is active'), giving an agent context for when the operation is meaningful. It does not name alternative tools or explicitly state when not to use this one, so usage guidance is clear but not exhaustive.

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