index_health

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

Annotations already declare readOnlyHint and openWorldHint, and the description reinforces rather than contradicts them by spelling out what 'read only' means here (never submits a sitemap or requests indexing). It also adds genuinely non-obvious operational context the annotations cannot convey: per-page URL Inspection call consumption, which is a real quota consideration when choosing `pages`.

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 guiding question, then the scope, then the safety/cost caveats — a sensible order with no filler. The long parenthetical enumerations of returned fields add bulk but each item is informative, so trimming would cost real signal.

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?

With no output schema, the description does its job by naming the return payloads (sitemap list, per-page index verdict, and a plain-language `problems` list) and disclosing the Vision-style cost of URL Inspection calls. Only real gap is the required `site` parameter's accepted format, which an agent needs before it can call the tool 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?

Schema coverage is 0%, so the description must carry the load, and it partially does: `pages` is explained as 'top pages by clicks' and `days` as the lookback window, and the cost note ties `pages` to quota. But `site` — the one required parameter — gets no format guidance (property identifier vs URL, sc-domain syntax), and defaults for `days`/`pages` are left to the schema.

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 diagnostic question plus the two concrete resources it returns: Search Console sitemap entries (errors, warnings, last read, URLs submitted) and index status per page (verdict, coverage, last crawl, canonical). The 'healthy in Google's index' framing plus sitemap/index-status detail clearly separates it from siblings like core_web_vitals, traffic, or search_queries.

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?

Usage is implied rather than stated: the opening question frames it as a diagnostic check, and the cost note ('each page checked uses one URL Inspection call') hints at a scoped/sampled run. But no sibling is named and there is no explicit when-to-use / when-not-to-use routing, so the agent must infer that this is the index-diagnosis entry point rather than a metrics or vitals tool.

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