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

Annotations only cover readOnly and openWorld, so the description carries the rest and does deliver: it discloses a live check per URL (a costly, outbound operation), a 100-URL cap, sampling depth of top 20 live checks and top 10 for index status, and the 3-click/20%-retention threshold. It omits expected latency or failure behavior for the live checks, which keeps it off a 5.

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?

Every sentence carries content, but the structure is weak: an awkward fragment ('100 known URLs a run in a fixed order'), then a second feature tacked on with a bare 'Also:', and the baseline instruction buried mid-paragraph. The two distinct outputs should be split, and the primary action front-loaded.

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 must explain returns and does – labels (fix/check/expected/indexed), sort order, and the lost-click cohort definition. Only the paging contract of detail/offset is left entirely to the schema, which is acceptable given 100% parameter coverage.

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%, so the baseline is 3. The description adds meaning on top by tying the 28-day windows to start_date/end_date semantics and by advising the agent to keep the 'full' result for later comparison, which gives the detail parameter operational intent.

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 names a specific resource domain – Google indexing reasons for up to 100 known URLs plus lost-click pages – with enough detail (fixed ordering, labelling, sorting) that an agent can tell what it returns. It never names a verb like 'fetch' or 'list' and never references any sibling tool, so differentiation comes only from the domain wording.

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?

It gives explicit timing guidance: use for a first baseline and then weekly, keep the full result, and compare by URL and reason to detect new reasons. That is concrete usage context, but no sibling alternative (e.g. seo_compare or seo_report) is named for related tasks.

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