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

Annotations only declare openWorldHint=false and destructiveHint=false; they do not declare readOnly, and there is no readOnlyHint. The description adds genuinely useful behaviour: results are cached per company + account + window + charge, and it reveals that an agent is run behind the scenes ('do not re-run the agent'), hinting at cost. It does not say what permissions are needed, what happens on a cache miss, or how the cache is invalidated.

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 tight sentences, front-loaded with the core behaviour and followed by a caching rationale. The only waste is the redundant lead 'SummarizeCampaignWindow summarises', which restates the tool name before getting to the point, and the whole thing arguably under-specifies rather than over-explains.

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?

An output schema exists, so return values need not be documented, which lifts some burden. However, with 6 fully undocumented parameters, all-optional inputs, and only partial annotations, the description does not fully equip an agent to call it correctly (e.g. what provider to pass, whether all params are required for the cache key).

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 0% across 6 parameters, and none have inline descriptions. The description partially compensates by naming company, account, window, and charge, which maps loosely to companyId, accountId, periodStart/periodEnd, and chargeAmount, but it says nothing about provider (the only enum), the date format/locale, or which of the charge parameters selects the charge.

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 object: it summarises one charge against the campaigns falling in its billing window. That is distinguishable from ads_insight_summarize_ad_spend in principle, but it never names or explicitly differentiates itself from the per-provider campaign-window siblings, so an agent must infer the boundary.

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?

There is no explicit when-to-use, no when-not-to-use, and no named alternative among the many ads_/google_ads_/meta_ads_ campaign-window tools. The only usable cue is 'repeated panel opens', which implies a display-time summarisation context, but this is inferred rather than stated.

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