Metric Breakdown

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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds useful return-shape context ('sorted list with counts, percentages, bounce rate, and session duration') beyond the annotations, but does not disclose the sort order, default date-range behavior, or pagination semantics — minor given the schema covers page/limit defaults.

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?

Three sentences, purpose first, followed by the dense parameter-mapping guide and the return format. No filler or repetition of schema content. The middle sentence is a long enumeration, but each mapping earns its place; a table might be marginally cleaner but the prose is efficient.

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?

For a read-only breakdown tool with 10 parameters and full schema coverage, the description covers the essential decision points: what the tool does, which parameter to use for which intent, and what the response contains (important since there is no output schema). The only notable gap is unspecified default date-range behavior when no dates are supplied, though the schema documents the mechanics of the date parameters.

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%, so the baseline is 3. The description adds genuine semantic value by grouping the parameter enum into intent-based categories, helping an agent choose the right dimension for a given analytical question rather than just listing allowed values. This is exactly the kind of meaning the raw schema cannot convey.

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?

States a specific operation — getting a metric breakdown by a chosen dimension — and enumerates the dimension categories, which clearly conveys the resource and scope. However, it does not explicitly distinguish itself from overlapping siblings like get_page_titles, get_session_locations, or get_user_event_breakdown, so an agent could hesitate about which tool to pick for page or geo data.

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?

Provides unusually strong parameter-level guidance: it maps intents (top pages, tech stats, geo, marketing, traffic sources, user flow) to specific parameter values, which is exactly the kind of when-to-use instruction agents benefit from. It stops short of a 5 because it gives no tool-level selection guidance (when to prefer this over get_overview, get_page_titles, or get_session_locations).

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