list_phones

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

The readOnlyHint annotation already declares that this is a safe read, so the description doesn't need to restate that. What it does add is the auth gating: the call fails without PROOF_API_KEY or an active session from start_login, and the session can be opened with start_login before retrying. That is genuine operational context, though it reads as server-wide boilerplate rather than tool-specific behavior such as ordering or empty-list handling.

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 opens with the one-line purpose, which is the right front-loading, then puts the access caveat second. Both sentences carry information, although "a session opens this tool" is slightly awkward phrasing for what is really "an existing session authorizes this call."

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?

This is a zero-parameter read tool with an output schema, so the description does not need to describe the returned phone records. The auth prerequisite is the main thing an agent could trip on, and it is covered. Only minor gaps remain, such as whether results are ordered or whether an empty account returns an empty list.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline applies. The description correctly implies the only implicit input is the authenticated account context, and it does not invent parameters that don't exist.

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 gives a specific verb and resource ("List all phone numbers") plus a scope ("associated with the authenticated account"), so the agent knows exactly what it returns. It does not explicitly distinguish itself from siblings like list_emails or remove_phone, but the resource noun is unambiguous enough that confusion is unlikely.

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 second sentence covers a prerequisite (an authenticated Proof account) and two ways to satisfy it, PROOF_API_KEY or start_login. That is login guidance rather than when-to-use guidance: nothing says how this differs from start_add_phone, remove_phone, or set_primary_phone, or when an agent should list rather than mutate.

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