Web Vitals

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds useful return-shape context by disclosing the percentile levels, which matters since there is no output schema. However, it does not disclose default time-window behavior when no dates or pastMinutes are supplied, nor how the filters interact with the dimension breakdown. It adds some value beyond annotations but not rich behavioral context.

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?

Two sentences totaling roughly 30 words with zero filler. The core function (metrics + percentiles) is front-loaded, and the optional breakdown capability follows. Every phrase earns its place, and nothing from the schema is redundantly repeated.

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 an 8-parameter tool with no output schema, the description partially covers return values (metric names and percentiles) and the optional dimension behavior. The main gaps are the default time-range behavior when neither date range nor pastMinutes is provided, and the lack of an explicit pointer to the rybbit_get_performance_timeseries sibling for time-series needs. It is adequate but leaves an agent guessing about a key runtime default for a moderately complex query tool.

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 description coverage is 100%, so the baseline is 3 and the schema carries the documentation burden. The description's 'break down by page path, browser, or OS' loosely maps to the dimension enum values (pathname, browser, operating_system), which is mildly helpful but largely restates what the schema already says via 'Break down performance by dimension.' No additional parameter semantics are contributed.

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 uses a specific verb ('Get') with a precise resource ('Core Web Vitals performance metrics') and enumerates the exact metrics (LCP, CLS, INP, FCP, TTFB) and percentile levels (p50, p75, p90, p99). This clearly separates it from siblings like rybbit_get_errors or rybbit_get_overview, and the percentile framing hints at an aggregated distribution rather than the time-series shape of rybbit_get_performance_timeseries.

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 when to use the tool (when you need Core Web Vitals percentile data, optionally broken down by dimension), but it offers no explicit when-to-use vs. alternatives guidance. It never names rybbit_get_performance_timeseries or rybbit_get_metric as alternatives, nor states exclusions such as 'use the timeseries sibling for trend data over time.' The context is clear but entirely left to inference.

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