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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the "[read-only]" prefix adds nothing and earns no credit. The description does add value beyond structured fields by disclosing the returned content categories (agent name, reason, outcome) and the underlying endpoint. It omits the time window, ordering, volume, and pagination behavior, which matter for an activity feed.

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 content categories and the primary use case are front-loaded, and the endpoint wrapper in parentheses is clearly demarcated as metadata. The first sentence is dense with three separate payloads crammed together, but there is no filler and nothing is repeated from the annotations except the redundant read-only tag.

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 a single optional parameter, no output schema, and full annotation coverage, the description is close to complete: it enumerates the three things returned and states the read-only audit purpose. The remaining gap is the undefined recency window and lack of any note on result size or ordering, which an agent would need to interpret the feed correctly.

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% and the single brandId parameter already documents the "personal" value and default behavior, so the schema carries the burden. The description mentions "the owner's" ceilings implicitly but never explains brandId scoping or what happens when the default brand differs from an explicit one, adding little beyond the schema. Baseline 3 applies when the schema is this well documented.

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 names a specific resource set: recent agent actions on ads (with the fields agent name, reason, outcome), still-pending owner approval requests, and the owner's agent ceilings. That is concrete enough to distinguish it from mutation siblings like decide_approval and from ads_insights, though it never explicitly names an alternative tool and bundles three datasets under one vague verb-less noun phrase.

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?

"Use it to see whether an approval request was decided" gives one clear use case, which is more than nothing. But there is no when-not guidance, no pointer to siblings such as list_approvals or decide_approval for the actual decision path, and no indication of how "recent" the window is, so an agent must infer the boundary between reading activity and listing approvals.

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