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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: results render as inline charts automatically, and click/conversion definitions differ for web_url (website) deeplinks, which changes how to interpret output. It omits response shape details and any limits, keeping it short of a 5.

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?

Four front-loaded sentences with no filler: capability, rendering behavior, a domain caveat, then prerequisites. Minor redundancy in repeating the list_deeplinks pointer that already appears twice in the schema keeps it from a 5.

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 8 parameters, three required, and no output schema, the description does the necessary work by naming the supported metrics, flagging the ltv-requires-ltvType dependency implicitly, and explaining that output renders as inline charts. A brief note on what each metric's result contains would close the remaining gap.

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 100%, so every parameter is already documented in the schema, including range clamping for ltv and deeplinkId's conditional requirement. The description adds only the looser restatement "use list_deeplinks first to find a deeplink id when one is needed," which the schema already says per-parameter. 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 opens with a specific verb+resource ("Query analytics for deeplinks") and enumerates the exact metric families (clicks, conversions, users, sources, geography, KPIs, LTV cohorts) that map one-to-one onto the metric enum. An agent can distinguish it from generic siblings like execute_query or run_insight_query without opening the schema.

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 gives concrete prerequisites: call list_deeplinks first to obtain a deeplink id, and load the understand-deeplinks skill before use. It also scopes the web_url case where conversion rate and LTV "aren't meaningful." The only gap is that it never states when to prefer a different analytics tool over this one.

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