List keywords

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

Annotations already cover the read-only, idempotent, non-destructive safety profile, so the bar is lower. The description still adds real behavior: archived keywords are returned and are marked archived=true (i.e. results are not filtered to active only), and negative keywords are distinguished via match_types values such as EXACT_NEGATIVE/PHRASE_NEGATIVE.

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?

Three short lines, front-loaded with the core action and scope, then the two most useful filter/state facts. Slightly telegraphic phrasing ("match_types filters, e.g. ...") but no filler.

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?

An output schema exists, so return values need not be described. For a read-only listing tool with an output schema the description is nearly sufficient; the remaining gap is that every parameter is optional and the description never says which identifier is needed to get a useful result, nor how max_results bounds the listing.

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% across six parameters, so the description carries the burden and only partly discharges it. It explains match_types with concrete example values and maps the three scopes onto ad_group_id / ad_group_ids / campaign_id, but ad_account_id and max_results (default 500) are never mentioned, nor is whether these selectors are mutually exclusive.

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 opens with a specific verb and resource ("List keywords and negative keywords") and states the three supported scopes: one ad group, several ad groups, or a campaign. That distinguishes it cleanly from the write-side siblings (create_keywords, create_negative_keywords, archive_keywords), though no sibling is named explicitly.

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?

Usage is implied by "List" and by the scoping options, and the match_types example hints at the retrieve-negatives-only case. But there is no explicit when-to-use / when-not-to-use guidance, no mention of when to prefer this over get_keyword_metrics or suggest_keywords, and no note on which of ad_group_id / ad_group_ids / campaign_id to supply.

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