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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. What the description should add but does not: whether nested objects like incoming are replaced wholesale or merged, whether omitting outgoing leaves it untouched or clears it, and whether recording controls can be disabled. For a destructive mutation with deep nested payloads, that silence is a real gap.

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?

One front-loaded sentence with no filler, which is good structurally. However, the brevity crosses into under-specification rather than conciseness: 'customer-facing' adds ambiguity rather than information.

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?

A destructive, non-idempotent mutation with nested objects, no output schema, and zero parameter documentation. The description leaves the agent unable to know what a partial payload does to existing rules or how the outgoing and recording blocks interact with the number's current state.

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% across four parameters, three of which are nested objects containing enums (when_called), arrays (allowed_agents, allowed_countries), and a boolean (can_be_used_as_caller_id). The description mentions none of these, so the agent gets no meaning beyond raw field names – exactly the case the description is supposed to compensate for.

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?

It states a specific verb and resource (update Number rules) and scopes it to one phone number, so the basic intent is legible. But 'Number rules' is never unpacked – nothing indicates that the rules comprise incoming routing, outgoing permissions, and recording settings, which is the real substance of the operation. The read counterpart get_number_rules is never mentioned.

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 statement of when to use this versus get_number_rules (read) or request_number (provision), and no prerequisites or caveats are given. An agent must infer entirely from the name that this is the mutation path for an existing number.

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