legal_verify

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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: it is a live network probe, it is read-only, and it checks 200 status, per-language responses, support email presence, and placeholder absence. It stops short of failure/timeout behavior, auth needs, or what counts as a hard failure.

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?

A single front-loaded sentence led by the 'LIVE read-only' qualifier, with no filler. Slightly dense/run-on, but every clause contributes a testable assertion.

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?

The output schema covers return values and there is only one parameter, so the description need not explain results. It conveys the core checks, but omits which page types/URLs are enumerated and how failures surface, leaving an agent short of what it needs for confident invocation.

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% for the single required parameter app_dir, so the description must compensate and does not. It never explains what app_dir points to or how languages are derived from it; 'per app language' only loosely implies it is a directory containing localized pages.

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 states a specific verification resource (privacy/terms pages per app language) and the concrete assertions made (HTTP 200 in the correct language, support email present, no placeholder). 'LIVE read-only' hints at differentiation from static siblings like legal_check/legal_render, but it never names them or the verb 'verify' explicitly.

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 run this versus legal_check, legal_render, or metadata_listing_check, and no prerequisites (e.g., pages must be deployed first). 'LIVE' implies it targets deployed URLs, but that is inference rather than guidance.

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