check_indexing_issues

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, so the safety profile is covered. The description adds genuine value by disclosing that results are grouped into named issue buckets and that site_url falls back to the GSC_SITE_URL environment variable, but it omits practical traits such as how many URLs can be checked at once, whether each URL is fetched live (and therefore slow), and any quota behavior.

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 purpose and the bucket list come first, with parameter notes compactly separated into an Args block; there is no filler. Slightly abbreviated prose style, but every line carries 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?

Because an output schema exists, the return shape need not be explained, and annotations cover safety, so the description is close to sufficient for a 2-parameter tool. What is missing is scale and cost context — how many URLs are reasonable and whether live fetching makes this a slow, open-world call — which matters for an agent deciding between this and a single-URL sibling.

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?

With schema description coverage at 0%, the description must supply the semantics, and it largely does: site_url is defined as the 'exact property' with an explicit fallback, and urls is explained as either newline-separated text or a JSON array, matching the anyOf string/array schema. It does not address the empty-string default for urls or any maximum URL count.

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 concrete verb and resource ('check several URLs') and, more usefully, enumerates the outcome buckets (not indexed, canonical mismatch, robots blocked, noindex, fetch errors, rich-result issues), which makes it distinguishable in output shape from siblings like check_url_status or get_index_coverage. It stops short of naming a sibling it is not, so it is clear but not explicitly differentiated.

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 implies when this is appropriate (diagnosing indexing problems across multiple URLs) but never states when to prefer it over batch_url_inspection, inspect_url_enhanced, or check_url_status. The only conditional guidance given is the site_url default, which is about parameter setup rather than tool selection.

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