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

Annotations already declare readOnly/non-destructive/closed-world, and the description is consistent with that by stressing it proposes only and mutates nothing. It adds genuine behavioral context annotations cannot carry: the funding caps ('draws only on what pauses free and the approved total leaves'), the no-repeat rule for prior or rejected proposals, the once-a-day limit on budget raises, and that the call is free.

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 opening clause fronts the trigger well, but the rest is a single dense paragraph mixing a hard-to-parse metric list ('and, past the click, visits, signups and cost per signup, and the changes…') with policy rules. The cap and dedupe rules earn their place, yet the tangle of nested qualifiers ('2x the plan's expected cost per signup, at least $5 and at most 75% of its budget; half its budget when…') would read far better as a short list.

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 describe returns, and it does: the metric set per ad group and the three proposal types with their trigger conditions. Caps, dedupe and the propose-only contract round out the model. Only the shape of the response (one proposal per ad group? an empty list when nothing qualifies?) is left unspecified.

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?

There is a single optional parameter and schema coverage is 100%, with the schema already explaining that id defaults to the latest boost. The description adds no further meaning about the id — no note on what identifies a boost or what happens if it is omitted when multiple boosts run. Baseline 3 applies since the schema does the work.

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 and resource — the daily check on a running boost — and enumerates exactly what it returns (per-ad-group spend, impressions, clicks, visits, signups, cost per signup) plus the change proposals it drafts. The parenthetical reference to boost_record and the proposal categories (pause/budget/duplicate) make it unmistakable against siblings like boost_results or boost_change.

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?

Gives an explicit trigger and ordering: run it after today's numbers are recorded in boost_record. 'Proposes only: the founder approves each and makes it in Ads Manager' implicitly separates it from any apply/change tool. It stops short of naming an alternative sibling (e.g. boost_change) or stating when not to run it, so it is not a full 5.

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