splithub_analytics

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

With no annotations, the description carries the full burden and does well: it discloses that self-hosted projects return raw counts only with analysis.available false, that counts must not be treated as experiment verdicts, that '(none)' means direct traffic, and that compare returns previous.range. It does not mention auth requirements, rate limits, or how large result sets are truncated, which leaves some behavioral gaps for a 12-parameter reporting tool.

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?

Nearly every clause carries information, and the without-property/with-property/with-by branching is reasonably front-loaded. However, the text is a single dense run-on with nested parentheticals that makes it hard to parse and re-read while invoking the tool.

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 12-parameter tool with no annotations and no output schema, the description covers most of what an agent needs: result shape for the no-property and with-property modes, dimension semantics for app screens, filters, segments, comparison ranges, and self-hosted caveats. Missing are the limit parameter's effect and any note on result caps or ordering, which are the main remaining gaps.

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 only 58%, so the description must compensate, and it largely does: it explains by, key (for trait), goal (per-row goal counts), compare formats including the date-range pattern, filters value syntax with an example, segment lookup, and experiment for variant. The limit parameter is never explained, and the interplay of days with from/to is only loosely implied ('Range: days (last N days) or from / to').

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 clearly establishes a read-only analytics report over properties, sites, or apps, returning totals, goals, topPages, and topSources. It distinguishes itself from experiments and implicitly from funnels/paths/retention by describing the shape of the returned visit metrics. It does not explicitly name the sibling analytics tools, so differentiation is inferred rather than stated.

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 branch conditions: omit property to list every property with a 30-day summary, supply property for full reports, use by to group rows, compare for period deltas, segment to apply a saved segment. However, it never says when to prefer splithub_analytics_funnel, splithub_analytics_paths, splithub_analytics_retention, or splithub_analytics_realtime over this tool. The warning 'These are counts, not experiments: no verdicts' is a valuable usage constraint but is the only explicit exclusion.

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