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

Annotations already cover the safety profile (destructive=true, readOnly=false, idempotent=false), and the description adds genuinely new context: default match type BROAD, the enum of allowed match types, duplicate-skipping behavior, and a human-approval gate. The duplicate-skipping note sits in mild tension with idempotentHint=false, but it is not a direct contradiction since deduplication is about entries within the list, not repeated-call effects.

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?

A single dense sentence with no filler; the action verb comes first, the `[publish]` category tag is front-loaded, and each parenthetical clause carries distinct information (identifiers, match type, dedup, approval). Nothing is wasted.

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 destructive, approval-gated mutation with four parameters and no output schema, the definition covers identifiers, defaults, and dedup, but says nothing about the approval workflow (sync vs async, how to confirm), return values, or limits on how many keywords can be added. Adequate but with clear gaps an agent would likely hit.

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?

With schema description coverage at 0%, the description carries the parameter burden and mostly does: it names the two identifier parameters as alternative list selectors, and gives the match-type values (EXACT / PHRASE / BROAD) plus the default. It leaves gaps — it never states that at least one list identifier is required, nor does it describe the required `ads_negative_keyword_texts` array or any batch-size limit.

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+resource ("Add keywords to a negative keyword list"), which is unambiguous and clearly a write operation. It does not name or contrast with the read-side sibling `list_ads_negative_lists`, so sibling differentiation is only implicit via the name and the `[publish]` tag.

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 rather than stated: it tells you the target list is identified by either `ads_negative_list_id` or `ads_negative_list_uuid`, and that a human approval step is required before committing. There is no explicit when-to-use/when-not guidance or pointer to alternatives.

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