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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), the description discloses key behavioural traits: it never guesses line type, returns null with a reason, does not check number assignment or reachability, and operates offline. It also tells the agent about pricing and auth requirements, which affect whether the tool can be invoked. This is rich, non-redundant context.

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 description is longer than average but every major clause contributes: main purpose, output semantics, confidence caveat, offline limitation, required input, and authentication. It is front-loaded with the core purpose and moves to edge behaviour and operational details. The pricing/auth sentence is slightly dense but still earns its place for invocation feasibility.

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?

Given that an output schema exists and annotations cover read-only, idempotent, non-destructive behaviour, the description still provides the missing operational and behavioural context: offline nature, no assignment checking, line-type null semantics, required phone input, and payment/auth model. An agent has enough detail to select and invoke 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?

The schema already describes 'phone' as a string, and coverage is 100%, so the baseline is 3. The description adds real semantic value by explaining that the input may appear in many typed formats and will be normalized to E.164, including stripping spacing, brackets, prefixes, and trunk zeros. It also highlights 'Required input: phone', reinforcing the one required parameter.

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 clearly states a specific action — normalise any phone number to E.164 — and enumerates the output: country, calling code, national number, line type. It distinguishes the tool's unique niche among the sibling set (no other phone-related sibling exists), and the 'knowable' framing communicates scope. No ambiguity about what the tool does.

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 description gives clear contexts: use for normalizing messy phone input and extracting knowable attributes; use with the expectation that it is offline and does not verify assignment or reachability. It explicit conditions for line-type reporting ('ONLY for countries whose ranges are unambiguous') and tells the agent that null is a valid, intentional response. It does not explicitly name an alternative tool, but no close alternative appears among siblings, so the gap is minor.

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