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

The annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description should add aggregation semantics, the time window, and response shape. It adds none of these; the only non-redundant text is a pointer 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 path is repeated verbatim at the start of the description, which is pure waste; the operation ID and describe_operation pointer fill the rest of the space that could have gone to useful content.

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 free-form query object, no output schema, and no explanation of what a 'summary' returns, the description leaves an agent unable to tell what data to expect or how to scope the request. It is inadequate for the tool's complexity.

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 both parameters (a free-form 'query' object and an empty 'params' object) are undocumented. The description doesn't explain what can go in 'query', but 'describe_operation provides native request schemas' does at least point the agent to where the schema lives, which is a small amount of compensation.

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 just restates the tool name and path twice ('GET /api/expenses/summary') without saying what the summary contains (totals? by category? by period?). It doesn't differentiate this tool from close siblings like get_expenses_period_overview, get_expenses_trends, or get_dashboard_expense_breakdown.

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?

It doesn't say when to use this tool instead of the many sibling expense tools. The only pointer is to describe_operation for request schemas, which is guidance on how to inspect the operation rather than when to select it.

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