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

Beyond the annotations, it discloses duration (a few minutes, up to ~20 minutes in 'researching' state), what side effects occur (creative built plus a PAUSED campaign), explicit non-effects ('never turns anything on and never spends ad budget'), and auth/plan requirements ('Needs the May plan and an X-Mako-Key header'). This is rich behavioral context that annotations alone do not 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?

The purpose and deliverable are front-loaded in the first sentence, and subsequent sentences each add distinct value (duration, non-effects, prerequisites). It is somewhat dense and could tighten the repeated 'portal' references, but nothing is filler.

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 no output schema, the description must carry the full burden, and it does: it explains what is produced, where it lands (the portal), the observable status, timing, safety posture, and required auth. An agent has everything needed to invoke it 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 coverage is 80%, so the schema already documents brief, avoid, feature, objective, and client_account_id. The description adds no per-parameter syntax or format guidance, so the baseline 3 for high schema coverage applies.

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 states a specific verb and resource ('Start a May creative run') and enumerates the deliverables (research, copy, eight ad concepts). It distinguishes itself from siblings like build_paused_campaign by clarifying that May builds creative and separately a paused campaign.

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 a clear prerequisite ('client needs a confirmed brand profile first, which is filled in at makometrics.com/portal') and implies the research-before-run path when a competitor is named. It never explicitly names alternative tools (e.g. set_brand_profile, list_clients) for the unprepared case, so it stops short of full when/when-not routing.

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