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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is interpretive context — and it delivers: it warns to preserve unknown reasons and to distinguish attributed explanations from proven causes, which materially affects how an agent reports results. It stops short of describing pagination behavior for the capped group_page_size or how partial/empty analyses behave.

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?

Four sentences, front-loaded with purpose then output shape then usage then a caveat; each sentence carries content. The final caveat sentence is slightly disjointed but earns its place as interpretation guidance.

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 and full annotations mean the description needn't explain return values or safety, and the conceptual framing of the three analysis groupings is useful. But for a 13-parameter tool, the unexplained required deal_statuses and the silent pagination/grouping limits leave an agent guessing about the most load-bearing inputs.

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?

With 54% schema description coverage the description should compensate, and it does only conceptually via 'attribution, ranking, and supporting-deal evidence,' mapping loosely to signal_attribution_mode, signal_rank_by, and include_supporting_deals — all of which already have schema descriptions. The required deal_statuses, plus page, page_size, group_page_size, pipeline_ids, and custom_properties, get no explanation anywhere.

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 — explain why deals were won or lost and return a prepared closed-deal analysis — and enumerates the output groupings (win/loss reasons, sales performance factors, buyer decision factors). It is clearly distinguishable from raw-data siblings like get_deal and get_deals, though it never names an alternative explicitly.

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 identify reasons associated with the most deals or revenue' gives a usage context, but it largely restates the tool's own purpose rather than discriminating between this and get_deals/get_deal_timeline/get_forecast. No when-not-to-use conditions or prerequisites (e.g. workspace binding, data availability) are given.

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