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

Annotations already declare readOnlyHint=true, but the description adds genuinely non-obvious behavior: independent per-axis reporting, empty-vs-blocked distinction, and especially the data_availability taxonomy where 'no_rows and access_error do not mean zero' — that prevents a serious misinterpretation. It also flags externally-authored strings as data, not instructions. It loses a point because the idempotency paragraph is generic boilerplate awkwardly grafted onto a read-only, zero-required-parameter call, and the phrase 'not available to anonymous taste calls' is irrelevant template bleed that adds noise rather than transparency.

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?

Well front-loaded: purpose, asset list, read-only status and the 'call this first' rule all land in the first three sentences. But roughly a third of the text is reusable idempotency boilerplate that does little for a read-only status call, plus an unexplained Korean trailing line about token consumption, so several sentences do not earn their place.

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 carries the burden of describing the return value, and it does reasonably well: per-axis asset lists, the data_availability status set with semantics, and the note that some lists start empty. What is missing is the concrete shape of a per-axis entry (e.g., whether blocked axes carry an error code or message), so an agent knows what to expect but not exactly what fields it can read.

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 both optional parameters are already documented, and the description's only parameter-adjacent content is the idempotency-key reuse rule (new key per new execution, reuse only to recover a lost response), which is useful. However, 'Takes no parameters' slightly understates the schema, which exposes an optional account_link_id that the agent may need when multiple connections exist; the description never mentions that escape hatch.

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 verb and resource ('Report whether the Google link is usable and list the assets it can read') and enumerates the five asset axes it covers. An agent can immediately distinguish this preflight/status tool from the dozens of google__ads__*, google__analytics__*, google__search_console__* and google__tag_manager__* siblings that operate on a single asset type.

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?

'Call this first: the other google tools only accept assets the customer selected for this link' gives an explicit ordering rule and the reason for it, and names the alternative family it gates. The follow-on notes about per-axis independence and empty Ads/YouTube/Tag Manager lists until features are enabled tell the agent what to expect rather than to retry or misread an empty result.

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