set_primary_phone

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so safety framing is covered. The description earns credit for disclosing what annotations cannot: the account/key requirement, the environment variable, and the sign-in-then-retry flow that otherwise would look like a failure. It loses a point for not saying what happens to the previously primary phone, which is the core destructive effect implied by destructiveHint=true.

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 well-structured blocks: the action statement first, then a clearly labeled ACCESS note, so the core purpose is front-loaded. The access paragraph is slightly longer than needed and its 'a session opens this tool' clause is awkwardly worded, but no sentence is 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 one-parameter mutation with an output schema, annotations covering safety, and auth explicitly documented, almost everything an agent needs is present. The remaining gap is the side effect on the incumbent primary phone, which matters given destructiveHint=true on a 'set primary' operation.

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% with a single required parameter already documented as 'Phone record ID to set as primary'. The description adds no format example, no indication of where the ID is obtained, and no note on whether the ID is account-scoped. Baseline 3 is appropriate when the schema carries the full parameter burden.

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: 'Set a phone number as the primary phone for the account.' An agent can distinguish it from list_phones, remove_phone, and start_add_phone without ambiguity. It falls short of a 5 because it never explicitly names which sibling to use first (e.g., list_phones to obtain the record ID) or contrasts itself with the parallel set_primary_email / set_primary_profile tools.

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 ACCESS block gives a real prerequisite: a Proof account via PROOF_API_KEY or an authenticated session through start_login, plus the notable retry pattern of calling the tool again after signing in. That is useful setup guidance, but it is auth logistics rather than when-to-use guidance — it never says when to prefer this over removing and re-adding a phone, nor that the id must come from list_phones.

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