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

The annotations already disclose destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the bar is lower. The description still adds useful context beyond the annotations: it says the call returns {integrationId, action:'set_name', status:'updated', kind, editUrl, message}, explains that names are non-unique free text, and describes how clearing works—details the annotations cannot show.

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?

The description is dense but free of filler: purpose first, then semantics, then return shape, then parameter sourcing. It is slightly load-bearing, and folding the return payload into prose makes the middle harder to scan, but every sentence carries necessary information.

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 3-parameter mutation with no output schema, the description covers the purpose, the clearing behavior, the return shape, and the source of every ID. The only gap is the failure behavior—for example, what happens when the ad_id is unknown or the project cannot be inferred—but the definition is otherwise complete.

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 33% (ad_id and project_id have no schema descriptions). The description compensates well: it explains that ad_id comes from list_ads, explains project_id's optional-inference behavior plus the project_id_required fallback to list_projects, and gives meaning to the empty-string name value.

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 uses a specific verb and resource combination: "set or clear the human-readable name of an ad." It then makes its scope clearer by stating what the tool is not ("Names are free-text and NOT unique"), so the agent can tell it apart from set_feed_name or set_marketplace_name among the sibling tools.

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?

It gives clear guidance on when to use the tool ("give an unnamed ad a memorable label, or to rename one") and when to pass an empty string ("to clear the name back to none"). It also gets the agent unstuck by naming list_ads and list_projects as sources for the IDs. However, it never explicitly says when NOT to use it or names a specific alternative tool, such as set_feed_name, for renaming feeds instead.

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