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

Annotations only supply readOnly/idempotent hints, and the description goes well beyond them: it discloses that unique_sessions are approximate due to daily-rotating hashing and summed day-by-day, that returning visitors count once per day, that networks can merge or split people, and that date ranges include partial days. It also defines worst_step_order and instructs quoting counts with every percentage, which is genuinely behavioral guidance not present in structured fields.

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 dense and largely telegraphic, with the returned metrics front-loaded and caveats following. Most sentences carry information, but the colon-style fragments and the trailing statistical warning about small counts, while useful, are slightly buried rather than structured into clear blocks.

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 analytics tool with no output schema, the description does a solid job enumerating the returned metrics, timezone rules, default range, and approximation caveats. It is missing only a concrete sketch of the response shape (e.g., how steps are identified in the output), which would fully close the 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains the complete-days default range and clarifies that trait filtering behaves according to the funnel's trait_scope field. It does not add much beyond the schema for project or funnel_id, but the trait and date semantics are enriched.

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 names a specific resource (one funnel) and enumerates exactly what it returns: per-step visitors, drop counts, conversion from previous and first step, and median times. It distinguishes itself from list_funnels by cross-referencing it for is_goal/goal_value semantics, but it does not differentiate from close siblings like preview_funnel or get_funnel_trend, which an agent could plausibly confuse it with.

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 useful usage context in the form of defaults (omit from/to for the last 28 complete days ending yesterday) and a warning that today is in progress and reads as a drop. However, there is no explicit statement of when to choose this over preview_funnel or get_funnel_trend, so the agent must infer the boundary from the return-value description.

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