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

Annotations already cover readOnly, idempotent, and non-destructive semantics, but the description adds genuinely new behavior: the Pro+ tier gate, that reads are free, the null-snapshot case for never-scanned sites, and the multi-country market scoping. The cooldown note pertains to run_rank_scan rather than this tool, which is a minor blurring.

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?

A single dense but efficient paragraph that front-loads what the tool returns before the constraints and parameters. No filler sentences, though the run-on structure and the trailing cooldown detail for a sibling tool slightly dilute focus.

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 appropriately enumerates returned data (domain metrics, Lighthouse scores, keywords, opportunities, history) and discloses the null-return case, so an agent knows what to expect. The missing link is explicit routing against get_rankings/get_traffic, which are present as siblings.

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 description coverage is 100%, so the schema already documents all four parameters, establishing a baseline of 3. The description only elaborates on market (reading one country of a multi-country scan), which largely restates the schema's 'when several were scanned', and says nothing about keywordLimit or opportunityLimit beyond 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?

Names a specific verb and resource (get the latest SEO Analysis scan) and enumerates its contents: domain metrics, Lighthouse scores, ranked keywords, opportunities, and monthly history. It does not, however, differentiate itself from lookalike siblings such as get_rankings or get_traffic, which could confuse selection.

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?

Provides real usage context: Pro+ only, free to read, returns a null snapshot when never scanned, and directs the agent to run_rank_scan to produce one (with a 24h per-country cooldown). It does not state when to prefer this over adjacent reporting tools like get_rankings or get_traffic.

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