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

With no annotations, the description carries the full burden. It does disclose useful behavior: a GET (hence read-only) endpoint, the x-temsor-pbx-key scoping requirement, and '$0 idle' cost. However, it omits pagination/limit behavior beyond the schema, return shape, and rate limits, and pads with marketing claims ('No DID sales', 'own PBX/Asterisk stays on customer') that add no invocation value.

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 purpose is front-loaded in the first sentence, but a large share of the remaining text is positioning copy ('No DID sales', 'Right-to-erasure ready', 'Advanced: own PBX/Asterisk stays on customer') that does not help an agent select or invoke the tool. Those sentences do not earn their 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?

For a read-only 5-param list tool with no output schema and no annotations, the description covers the data domain, auth scoping, and endpoint, which is the minimum viable. It stops short of describing return shape or result ordering/paging, and the noise displaces information an agent would actually need.

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 all five parameters (including include_extensions, which the description never mentions) are already documented in the schema. The embedded query-string params merely restate the schema, adding no syntax or format meaning beyond it. 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?

The first sentence names the resource and its content specifically: 'caller phones+names and extension identities seen on transfers,' and the endpoint path reinforces that this is a list operation over Person rows. It is clearly distinguishable in substance from pbx_persons_get, but it never names that sibling or any other, so differentiation is left to inference.

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 statement at all. The inline 'kind=caller|extension|all' is a parameter enumeration, not guidance about which tool or mode to pick, and the description never says when to prefer this over pbx_persons_get, pbx_facts, or pbx_search.

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