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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered structurally. The description adds nothing about what the history covers (time range, granularity, pagination, ordering) or what 'history' returns, beyond redirecting to describe_operation.

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 first sentence is duplicated verbatim, which is pure waste, and the operation ID adds no decision value. Nothing about purpose or behavior is front-loaded because there is no real content to front-load.

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 a nested free-form query object, no output schema, and 0% parameter documentation, the description is far too thin to call this endpoint correctly. The describe_operation redirect is a partial mitigation, but an agent still cannot tell what history window, grouping, or entity scope is expected without an extra round trip.

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 0% and the two top-level parameters are a free-form nested 'query' object with additionalProperties allowed plus an empty 'params' object, so the schema conveys essentially no semantics. The description does not compensate; it only points at describe_operation for native schemas, leaving the agent to make a second call to learn anything about filtering or paging.

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 only restates the tool name and endpoint path ("GET /api/portfolio-rollups/history") twice, with no verb-and-resource explanation of what the response contains or what a 'rollup history' means. An agent learns nothing beyond the URL segment, and nothing distinguishes it from siblings like get_portfolio_rollups_metrics or get_portfolio_rollups_snapshots.

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 statement of when to use this endpoint versus the other portfolio-rollup siblings (entities, metrics, snapshots) or vs. execute_read. The only actionable hint is that describe_operation can supply native request schemas, which is a prerequisite instruction rather than usage context.

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