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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), so the bar is lower, and the description adds genuine behavioral context by spelling out blast radius: the change affects only one ad group and explicitly not the campaign. It stops short of disclosing what happens on duplicate keywords (idempotentHint=false suggests duplicates accumulate) or what the call returns.

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?

Two sentences, zero filler, with the scope constraint front-loaded and the alternative-routing sentence placed second. 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 5-param mutation tool with nested objects, no output schema and full annotation coverage, the description handles the routing and scope questions well. It is slightly thin on post-call expectations (e.g. whether duplicates are deduped, what errors look like), which validateOnly partially mitigates in the schema.

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 60%: customerId, extraFields and validateOnly are well documented inline, while adGroupId, keywords and matchType carry no description. The description adds nothing about parameters, but the undocumented fields are largely self-explanatory, so this sits at the moderate-coverage baseline.

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 (add) and resource (negative keywords) plus a precise scope constraint ('scoped to a single ad group, not the whole campaign'), which cleanly separates it from the sibling add_negative_keywords. No schema opening is needed to tell the two apart.

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?

Explicitly gives the when-to-use condition ('a search term is wasteful for one ad group's theme but still relevant to another') and names the alternative for the opposite case (add_negative_keywords at campaign level, with the reason: fewer calls). This is exactly the routing guidance an agent needs.

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