check_tap_to_call

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

With no annotations, the description carries the full burden and does reasonably well: 'check' makes the read-only nature apparent, the verdict vocabulary is disclosed, and the scope limit ('plain-text UK numbers') is stated. It omits live-fetch behavior, timeouts, and how non-UK numbers are treated, so it falls short of complete.

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 purpose and return vocabulary are front-loaded and the description is compact. The one persuasive sentence about mobile visitors retyping numbers is rationale rather than instruction, and the Args block duplicates the schema, but given 0% schema coverage that repetition is compensation rather than waste.

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 need not be spelled out (though they are), and one parameter plus a read-only check is a simple surface. The remaining gap is the absence of any link to the broader audit siblings or notes on fetch/failure handling.

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 coverage is 0% for the single 'url' parameter, so the description must compensate; it does so by clarifying the expected value and giving a concrete example ('https://example.co.uk'). It stops short of stating constraints such as absolute-URL requirement or reachability.

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 precise verb+resource ('check whether the phone number on a page is a clickable tel: link') plus the exact failure mode it detects, which no sibling (check_form_platform, check_nap_consistency, audit_website) could be confused with. It also enumerates the verdict vocabulary ('ok', 'leak', 'no_phone_found'), pinning the tool's scope tightly.

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 mobile rationale implies when the check matters, but there is no explicit when-to-use statement and no routing against the audit siblings (audit_website, run_full_audit) that likely subsume this check. Usage must be inferred rather than read.

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