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

Annotations only state it's a non-read, non-destructive, non-idempotent write. The description adds substantial value beyond that: the automatic measurement model (28 days before vs after, site-adjusted), the 16-month backdating window, immediate measurement for old entries, and the 3-active-measures cap on free domains. This is exactly the behavioral context an agent needs before a mutating call.

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?

Front-loaded with purpose, then measurement behavior, then constraints and the safety warning. Sentences are dense but each carries actionable information; the only minor bloat is the parenthetical examples.

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 and 6 params, the description covers the mutation's consequences, timing rules, and quota well. The main gap is no guidance on the category enum's intended usage, but overall an agent has enough to call it correctly.

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 67% and the schema already documents date, title, pages, and domainId. The description's examples illustrate the title field but add no new meaning for the category enum or note parameter, so it only marginally exceeds the schema baseline.

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 and resource ('Log a change the user made to their website themselves ... on the history timeline') and immediately explains the downstream effect (28-day before/after measurement adjusted for the rest of the site). This clearly distinguishes it from siblings like timeline_events (read) or run_scan (scanning).

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 a clear condition for use (recording a change the user made themselves) and an explicit exclusion ('Never call this without an explicit user request'), plus backdating limits and free-tier quota. It doesn't name a specific alternative sibling for viewing existing events, but the when/when-not guidance is strong.

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