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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so 'Read-only' earns no credit as it merely repeats them. The genuinely additive detail is that results are returned in input order, which is real output-behavior information an agent would otherwise have to discover. It says nothing about partial failures or how individual domains that error are represented.

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?

Three short sentences, zero padding, with the batch scope and the sibling relationship front-loaded before the ordering and safety notes. Every sentence carries distinct information.

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 needn't be explained, and the tool is a single-parameter batch call, keeping the required scope small. What remains uncovered is error/partial-failure semantics across a 50-item batch, an unaddressed risk for a bulk tool.

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% (a bare string array), so the description must compensate: 'domains or URLs' usefully tells the agent both bare domains and full URLs are acceptable. It stops short of specifying format expectations (scheme required or not, subdomains, ports), which is the half of parameter meaning an agent would still guess at.

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?

Names the action (batch check), the resource (domains/URLs), and anchors it to the sibling check_domain so the agent knows this is the multi-input variant. The one gap is that 'check' never says what is being checked (availability, DNS, blocklist), so the agent must rely on the sibling's definition to infer the operation.

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?

'Batch version of check_domain for up to 50 domains or URLs' implicitly routes the agent: single item goes to check_domain, many go here, and the 50 cap bounds a single call. There is no explicit statement of when not to use it or what to do beyond 50 items (chunking).

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