Check a host against AdGuard filters

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description still adds useful context beyond them: it states no DNS query is sent and nothing changes, documents the upstream endpoint, explains how filter_list_id is resolved (0 = custom rules, negatives = built-in sources), and names the error codes. This is richer than a pure read-only declaration.

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?

Front-loaded with the core answer, then structured into endpoint, usage, returns, and errors sections — each sentence earns its place. It is on the longer side, but the labeled blocks make it scannable rather than padded.

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?

Covers what it does, how (upstream endpoint), what it returns (including the derived `blocked` and `filter_name` fields), and the failure modes. Output schema existence means the return explanation is a bonus rather than a necessity, and the error section is a genuine addition.

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 100% and the single parameter's format (no scheme, path or port) is already documented there, so the baseline is 3. The description adds value by tying the parameter to an error condition ('invalid_name' for empty or malformed domain), giving the agent a validation expectation the schema does not.

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?

States a specific verb and resource ('check whether AdGuard Home would filter a domain') and immediately differentiates itself from the sibling adguard_get_config by naming it as the wrong tool for full filtering setup. The agent can distinguish this from adguard_add_filter, adguard_remove_filter, and adguard_set_filter_enabled without opening any schema.

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?

Explicit 'Use when: explaining why a domain is blocked or allowed' and 'Not for: the full filtering setup — use adguard_get_config' give both the inclusion and exclusion criteria plus the alternative. Nothing is left to inference.

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