check_domains

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

With no annotations, the description carries the full burden and does well: it discloses that results are returned in input order (a key behavioral trait), that include_raw can produce 'large responses' (size concern), that caching is in-memory and TTL-based (implying cache can go stale), and notes parallel execution with rate-limit friendliness. This is richer behavioral context than typical.

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 compact and front-loaded: the first line states the core purpose and key differentiator (parallel bulk check, rate-limit friendly). The Args section uses clear docstring formatting, and the Returns line is a single efficient sentence. Every sentence earns its place with no fluff.

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 tool has an output schema that documents the return structure, so the Returns line adequately summarizes. The three parameters are all documented in the Args section with useful detail. Given the moderate complexity (bulk parallel operation with caching and raw payload options), the description covers the essential behavioral and usage context well, though it could note potential cache-staleness implications of use_cache.

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%, so the description must compensate for all three parameters, and it does reasonably well: domains has a max-recommended count, include_raw signals size tradeoff via 'large responses', and use_cache is described as 'in-memory TTL cache'. This adds meaningful semantic context beyond the bare schema titles, though it lacks nuance on what 'raw' actually contains.

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 the tool checks multiple domains in parallel, distinguishing it as a bulk operation. However, it doesn't explicitly differentiate from the sibling 'check_domain' beyond the plural/bulk implication, nor does it state what 'check' means (availability, DNS, WHOIS, etc.) — the verb 'check' remains ambiguous about the specific domain attribute being verified.

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 notes it's 'rate-limit friendly' and specifies a max recommended 50 domains per call, which gives useful context for when to prefer this bulk tool. However, it doesn't explicitly state when to use check_domains vs the single check_domain sibling, nor when to toggle include_raw or use_cache — the when/when-not guidance for these params is implied rather than explicit.

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