splithub_analytics_retention

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses the clamping behavior (over-90-day / over-26-week ranges are truncated and flagged clamped: true) and the meaning of retained[0] and the retained[i]/users ratio. It omits permission/authentication requirements and cost/latency expectations for a potentially heavy cohort query.

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?

One dense but well-ordered paragraph: resource, then start/return semantics, then output shape, then clamping caveat, then defaults and filters. No filler sentences, and the most decision-relevant facts (what it is, what it returns, what gets truncated) come first.

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 9-parameter cohort tool with no output schema, the description supplies the response structure, defaults, and truncation rules, which is most of what an agent needs. Remaining gaps are the undocumented segment parameter and the ambiguity between days and from/to that the description does not resolve.

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 44% across 9 parameters, but the description explains the two most confusing ones (start, return value grammars), the period default, and what filter dimensions are valid. It says nothing about segment, days, or how from/to interact with days (and days allows 400 while the description says ranges are clamped at 90 days), leaving real gaps.

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 resource (retention cohorts of an analytics property) with concrete semantics: users grouped by start (visit, event:<name>, goal:<key>) and how many returned in period 0, 1, 2… It even sketches the response shape (cohorts[] { start, users, retained[] }) and explicitly excludes experiment reporting ('Counts, not an experiment'), which distinguishes it from splithub_results/experiment_* siblings.

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?

Gives concrete defaults (start visit, return visit, period week) and states what filters accept (platform, app_version), plus an explicit exclusion ('not an experiment'). It does not directly name when to prefer this over splithub_analytics_funnel or splithub_analytics_paths, so the sibling routing is left partly to inference.

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