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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. Beyond that, the description adds concrete behavioral facts: closed deals are excluded, and it differentiates forecast_status (manual) from forecast_category (AI). This adds useful context without contradicting annotations.

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 description is three sentences with no waste. The core purpose is front-loaded, followed by the confusion-resolving Field terminology (forecast_status vs forecast_category) and the routing guidance. Every sentence earns its place.

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?

Given the output schema (not shown, so return values are documented elsewhere) and annotations that already cover safety, the description adequately covers the tool's purpose, scope, and relationship to siblings. It might mention pagination or result ordering, but those are typically covered by the output schema or defaults, so the description remains complete enough for correct agent selection and invocation.

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 only 50%, and the description does provide some parameter-level meaning (e.g., forecast_status is manual, the tool returns open-deal totals). However, it does not explain page, page_size, forecast_status values, pipeline_stages, or the exclusive selectors beyond their schema text. The added semantics are helpful but do not fully compensate for the half-undocumented parameters.

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 opens with a specific verb-resource statement: 'Return exact open-deal totals, configured manual forecast_status, and AI assessments.' It differentiates itself from siblings like get_deals by explicitly noting that closed deals are excluded and that forecast_status is manual while forecast_category is AI.

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?

The final sentence provides explicit routing: 'For target-attainment questions, consider won deals from the same scope and date range... get_deals returns those deal sets, get_win_loss explains outcomes, and get_deal provides one deal’s details.' This clearly tells the agent when to use alternatives, complemented by the observation that closed deals are excluded from this tool.

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