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

The description goes far beyond the readOnlyHint=true annotation by disclosing server-side fetching, the exact meaning of 'fetched' (true only when HTML was actually read), error categories ('unreachable', 'blocked'), and the drift-report semantics (statuses 'in_sync', 'outdated', 'unavailable' with bounded reasons). It also states that detected signals are NOT meaningful when fetch fails. This rich behavioral contract is absent from the annotations and schema.

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 long but information-dense, with purposeful structuring via colons and examples. It front-loads the core purpose and then uses conditional clauses to explain edge cases. No sentence is wasted; however, the density makes it moderately heavy to parse. It earns a 4 rather than 5 due to the complexity of the prose, but remains efficient for the tool's complexity.

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?

Despite the absence of an output schema, the description fully covers the result contract: 'fetched' semantics, 'fetchError' reasons, drift key with statuses and bounded reasons, and how to interpret each. It also explains when to treat results as unknown. For a tool with this complexity, this is outstandingly complete – the agent has all necessary context to act 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 provides full descriptions of both 'url' and 'appId' (100% coverage). The description adds value by explaining the behavioral consequence of appId: 'When provided (or when the page already carries the installed LexVibe snippet), the result includes a drift report.' It also mentions that url can be a bare domain, reinforcing the schema. No new parameter details are needed beyond the schema, but the behavioral linkage elevates it above the baseline.

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 'Free legal-compliance check of a public website' – a specific verb ('check') and resource ('website compliance'). It clearly distinguishes from siblings like check_ai_act and check_store by enumerating the detected data-processing categories (analytics, marketing pixels, payments, generative AI, email collection, third-party sharing) and the output (legal documents, cookie-consent setup, EU AI Act applicability). This leaves 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?

Provides explicit when-to-use guidance: 'Run it again after adding any SDK, analytics, payment, auth or AI integration.' It also explains when results are unreliable ('when false... report the check as inconclusive, not as clean') and how to handle the drift status 'unavailable' ('treat as unknown, never as in sync'). This gives the agent clear decision rules for invoking and interpreting the tool.

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