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

Annotations already declare a safe, idempotent read, so the description is free to spend its words elsewhere — and it does: data is read live rather than cached, "No figures" tells the agent no performance metrics come back, a null bid means the ad group default, and the pagination contract (follow `next_cursor` while `has_more` is true) is stated outright. These are behaviors an agent could not infer from the annotation block or the schema.

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 the scope constraint and the returned entity list, with no filler sentences; "No figures." is a crisp two-word exclusion. The single long sentence carrying both the field enumeration and the bid parenthetical is dense and slightly hard to parse, but nothing is redundant.

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 return-value burden and largely meets it by naming each target type and the bid/state fields, plus pagination and the no-metrics caveat. It stops short of saying how negatives or state values are represented, so an agent still meets some surprise in the response, but nothing needed to make the call 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 description coverage is 100%, so all five parameters are documented in structured form and the baseline is 3. The description adds only incidental meaning — currency of the bid field and the null-bid convention — and never mentions `ad_group_id` as a way to narrow within the campaign, which is the one parameter whose purpose (an optional filter) it could usefully have reinforced.

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?

Opens with a specific verb+resource+scope: "List ONE campaign's keywords and other targets, read live from Amazon", then enumerates exactly what is returned (keywords with match type, product targets/ASINs, categories, auto-targeting groups, negatives). This cleanly separates it from list_campaigns (which campaigns exist) and list_ad_groups (the ad-group layer) without needing to open a 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?

"Answers 'which keywords does this campaign target?'" gives a concrete use case, and "ONE campaign" plus the id-provenance in the schema implies the campaign must already exist and be identified first. There is no explicit when-not or named-alternative guidance (e.g. use list_ad_groups first to narrow to one ad group), which keeps it below a 5.

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