add_exact_keyword

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

The description goes beyond annotations by declaring the tool is 'PREVIEW ONLY' and requires 'explicit approval' before applying, and it disambiguates the optional bid behavior ('without it the ad group's default bid applies'). It doesn't state idempotency or whether re-adding an existing keyword overwrites/skips, which the annotations flag as non-idempotent, so the behavioral picture is strong but not fully closed.

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 tight sentences, front-loaded with the key safety constraint ('PREVIEW ONLY'), then the example source, then the bid fallback behavior. No filler and every clause earns its 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?

For a mutation tool with no output schema and sparse schema coverage, the description supplies the critical missing pieces: preview/approval workflow, example use case, and bid default behavior. It lacks details on duplicate-keyword handling and confirmation flow, leaving a small but real gap for a non-idempotent write tool.

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 only 20%, so the description has to carry most parameter meaning. It explains that 'amount' is an optional bid and that omitting it falls back to the ad group default, which is real semantic value. However, campaignId, adGroupId, and currency are left unexplained, so coverage of the low-documentation schema is incomplete.

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 names a specific verb ('add'), resource ('exact-match keyword'), code unit ('ad group'), platform ('Apple Ads'), and an example source (a converting search term from get_ads_search_terms). It clearly differentiates from siblings like add_keywords, add_negative_keyword, and add_rivals, which each target different keyword types.

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 explicit and conditional: it states the tool is 'PREVIEW ONLY', tells the agent to apply only with the user's explicit approval, and points to the specific upstream tool (get_ads_search_terms) that surfaces a converting search term. This gives the agent a clear 'when' and a safety gate for a mutation tool.

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