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

Annotations indicate readOnlyHint=false, which implies mutation, but the description doesn't add details about what happens during the update (e.g., whether it overwrites existing bids, atomicity, permission requirements). It mentions bulk support and partial_failure parameter but doesn't explain behavior like partial failure handling. Since annotations are minimal (no idempotent or destructive hints), the description carries more burden, but it falls short of explaining consequences or edge cases.

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?

The description is concise with two sentences, front-loaded with the primary purpose. It uses a line break to separate bulk support info, which is clear. However, the currency example could be omitted or expanded, but overall it's efficient without fluff.

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?

Given the tool has 6 parameters, no output schema, and minimal annotations, the description is incomplete. It doesn't explain return values, how to specify keywords (ad_group_id and criterion_id are required but not described), or the behavior of partial_failure. It covers bulk support but not the full context needed for correct invocation. The tool is relatively complex, so more detail is expected.

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 0%, so the description must compensate for parameter meaning. The description explains 'cpc_bid' via currency example but doesn't explain the 'keywords' array structure (ad_group_id, criterion_id), 'partial_failure', or 'customer_id' vs 'customer_ids' distinction. It mentions bulk support but doesn't clarify required parameters or relationships. This is insufficient given zero schema coverage.

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 clearly states the action ('Update max CPC for one or more keywords') with a specific resource (keywords) and a specific attribute (max CPC). It distinguishes from siblings like 'google_ads_keyword_update_status' which updates status rather than bid. The example of account currency ('1.5 = R$1,50') adds useful context for understanding the value semantics.

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?

The description provides some guidance on usage by indicating it supports bulk execution via customer_ids. However, it doesn't explicitly mention when to use this vs alternatives (e.g., when not to use, or mention of partial failure). It implies usage for updating bids but lacks exclusions or comparisons with sibling tools like google_ads_keyword_add or google_ads_keywords_diagnostics.

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