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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds real substance on top: keywords are created PAUSED by default so nothing starts spending, duplicates by text+match type are skipped (explaining the idempotent hint), and each keyword can carry its own bid or inherit the ad group's. This is exactly the behavioral context annotations cannot convey.

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?

Five tight sentences, front-loaded with the action and the most important behavioral fact (created PAUSED). Every sentence carries distinct information — no restating of the name or schema.

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?

No output schema exists, and the description adequately covers return-relevant behavior (what gets created, what gets skipped, dryRun preview). It is slightly incomplete on what happens with invalid/partial keyword batches and on the conditional accountId parameter, but nothing critical to calling it 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 coverage is 80%, so baseline is 3; the description goes beyond it by explaining the bid fallback ('otherwise it uses the ad group's'), per-keyword final URL, the 'Active' override of the default status, and the 50-per-call limit. Only accountId and error/partial-failure semantics go unmentioned.

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: 'Add keywords to an ad group.' The 'msads_' prefix and title identify the platform, so an agent can separate it from the generic 'add_keywords' sibling. It does not explicitly name the alternative tools (add_keywords, msads_add_negative_keywords), so it stops short of full sibling differentiation.

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?

Provides useful invocation context — dedupe skipping, the 50-item cap, and a recommendation to use dryRun to preview. But it never states when to prefer this over add_keywords or msads_add_negative_keywords, nor any prerequisites (e.g. ad group must exist and be enabled). Usage is implied rather than prescribed.

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