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

Adds substantial context beyond the readOnly/idempotent annotations: totals can exceed the sum of rows because Google hides rare queries, results declare which backend served them via `source`, and the 90-day stored-data boundary versus the 16-month SEObolt-allowance limit is spelled out. These are exactly the behavioural details that prevent an agent from misreporting numbers.

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 what is returned and immediately followed by the critical caveat about totals versus row sums. Every sentence carries information, though the single dense paragraph mixes return shape, cost model and auth prerequisites, which makes it heavier than it needs to be.

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?

There is no output schema, so the description has to describe the return values — and it does: metrics, selectable dimensions, previous-period comparison and the `source` field. Combined with the cost and connectivity notes, nothing an agent needs to call this correctly is missing.

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 earns an extra point by explaining semantics the schema cannot, notably that CTR is a percentage and average position is impression-weighted with lower being better, and by restating the default window (last 28 days by query). It does not go further into limit/sorting behaviour.

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 exact source (Google Search Console), the resource scope (one site), and the precise metrics returned (clicks, impressions, CTR as a percentage, impression-weighted average position), plus the dimensions available. This is specific enough to separate it from siblings like seo__analytics, seo__ranked_keywords and seo__domain_overview without needing to read any schema.

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?

Gives concrete usage guidance: defaults to the last 28 days by query, and 'ask for older dates only when the user does' because of the SEObolt daily allowance. Also states the prerequisite (a Google service account or SEObolt on the Integrations page) and what happens if absent. It stops short of naming an alternative sibling tool when GSC data isn't the right fit, so it lands at 4 rather than 5.

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