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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description is not required to restate it. What the description adds beyond that is modest: the fact that an app key is required and the list of metrics returned. It says nothing about currency/units, data freshness, or behavior when no usage exists in the window.

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 compact sentences with no filler, and the substantive content (what you get) leads. The first sentence is a noun-phrase fragment rather than a complete statement, which slightly weakens front-loading but costs nothing in clarity.

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 no output schema, the description carrying the returned metric list is the right compensation and makes the tool's payload predictable. For a one-parameter read tool whose annotations cover the safety profile, the remaining gaps (currency/units, how the app key is supplied) are minor rather than blocking.

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 100% with a single optional 'days' parameter (default 30, max 365) fully documented in the schema. The description only gestures at it with 'over a period' and adds no meaning about windowing, timezone, or how the daily series aligns with the range, so the baseline 3 applies.

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 enumerates the exact resource contents: AI cost, revenue, margin, AI share of revenue, request count, and a daily series for an app over a period. That is specific enough to separate it from a detailed breakdown or a single-model estimator, though it never states a verb or explicitly contrasts itself with siblings like get_cost_breakdown or get_plan_margins.

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?

Usage is only implied by the word 'overview' plus the period parameter; there is no explicit when-to-use statement or when-not-to-use exclusion pointing at get_cost_breakdown or estimate_llm_cost. The one genuine guidance element is the prerequisite 'Needs the app's key', which tells the agent a credential is required before calling.

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