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

Beyond the read-only annotation, the description discloses significant non-obvious behavior: it never returns person-level data, defines each funnel event with precise tracking criteria, warns about a known instrumentation change (2026-08-24) that can create false conversion jumps, states that timed-out steps report TIMED OUT rather than zero, and returns an error when analytics is unconfigured. This far exceeds what annotations alone provide and prevents misinterpretation of results.

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 description is long, but every section serves a purpose: front-loading the scope, then providing essential funnel event definitions, the instrumentation caveat, and timeout/error behavior. The structure is logical with a clear break after the metrics list. The only minor flaw is the enthusiastic tone (all-caps 'FUNNEL EVENTS') which adds a little noise, but it doesn't detract from usefulness.

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 must communicate what the result contains, and it does: it lists every metric, defines the funnel steps precisely, flags a known data discontinuity, and describes timeout and error semantics. For a tool with one parameter and no output schema, this is exceptionally complete — an agent can predict exactly what it will get back and how to interpret edge cases.

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?

The single parameter 'days' is fully documented in the schema (7, 28, or 90, default 7), so the description adds no new information about the parameter. It does put the parameter in context by mentioning it in the opening sentence, but that's redundant with the schema. With 100% schema coverage, the baseline of 3 is appropriate; the description adds no extra meaning beyond the schema.

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 explicitly states it aggregates marketing analytics over 7/28/90 days, enumerating the exact metrics and funnel steps. It names the resource (fleet analytics overview) and the action (aggregate), and distinguishes itself from any single-metric tool by the breadth of the output. There is no ambiguity about what the tool does.

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?

The description implies this is the top-level marketing analytics overview and mentions the supported time windows, but it never references sibling tools or explains when to prefer this over, e.g., fleet_product_funnel_counts or fleet_analytics_top_pages. There is no 'use this when' or 'for X use that' guidance; the routing is left to the agent to infer.

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