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

With no annotations at all, the description carries the full burden and does well: it discloses that prior routing is saved and restored on disconnect, that calls forward to forward_to with the shop number as caller ID, that voicemail happens by email after ring_seconds, and that Twilio falls back to ringing forward_to directly if Doing Work is down. That is genuine behavioral context beyond the schema. It still omits things like whether provisioning incurs cost or what disconnecting destroys, so not a 5.

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?

Purpose is front-loaded and the length is reasonable, but phrases like 'Doing Work saves where it pointed before' are cryptic and require guessing at what 'Doing Work' refers to. The fallback clause is also packed in without clear separation, slightly hurting readability.

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?

An output schema exists so return values needn't be explained, and the description covers the key behavioral facts (routing, voicemail, persistence, fallback, owner-only). The main gap is prerequisites, such as whether a Twilio connection must already exist, but overall it is sufficient to call the tool correctly.

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 0%, so the description must compensate, and it substantially does: forward_to is defined as the ringing target, ring_seconds as the delay before voicemail, and voicemail_email as the voicemail destination. It only weakly implies what phone (the number to use) means and says nothing about shop_id, but the core semantics are conveyed.

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 opens with a concrete verb+resource: use one number from the shop's Twilio account for texts and calls. That is a specific, distinguishable action and the agent can tell it apart from sibling number-management tools like phone_twilioNumbers. It never names a sibling explicitly, so it stops short of a 5.

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?

'Owner only' gives an important access gate, and the context implies this is for provisioning a shop's calling/texting number. But the description never says when NOT to use it, nor points to alternatives such as phone_twilioNumbers or phone_connectTwilio, leaving the routing decision to inference.

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