Iron/Out UX Score Benchmark

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

Annotations already declare a read-only, open-world call, and the description adds real substance beyond them: the 28-day CrUX window, the exact metrics measured, and the absence of lab testing. The return shape is also sketched (ranking plus a link), though limits such as data-unavailable domains are not covered.

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?

Three short sentences, front-loaded with the core action and data source, then usage, then a scoping exclusion. Nothing is redundant or padded.

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, the description usefully states that a ranking and report link are returned, and it pins down the data source and time window. It stops short of covering edge cases like sites with insufficient CrUX data, but is otherwise sufficient for correct invocation.

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% and every parameter is already documented in the schema, including the 2-5 URL cardinality and the category/language semantics. The description adds no syntax or format detail beyond what the schema provides, so baseline 3 applies.

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 gives a specific verb ('compares'), a concrete resource ('Iron/Out UX Score of 2 to 5 websites'), and names the underlying data source (CrUX, last 28 days, Web Vitals metrics). An agent can distinguish this from a generic benchmark tool without opening the schema.

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 states the intended scenario ('competitor or sector comparisons') and a clear exclusion ('runs no lab test or Lighthouse'), which is valuable negative guidance. It does not, however, name the sibling run_ux_benchmark or say when to prefer it, leaving the alternative implicit.

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

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

With readOnlyHint and openWorldHint already declared, the description still adds substantial context: the 28-day CrUX window, the five-metric weighting (TTFB/FCP/LCP/INP/CLS), the failure mode when traffic is too low to have CrUX data, and the conditional revenue-at-stake estimate. It also states the return shape (summary plus report link) despite no output schema.

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 and score definition, then usage, then limits, then optional-parameter behavior. Each sentence adds decision-relevant information — no filler or restatement of the title.

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?

No output schema exists, yet the description says what comes back (summary and full-report link). Combined with the stated data source, coverage limits, and scoring weights, an agent has enough to decide and call 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 100%, so the schema documents url, language and monthlyRevenue in detail. The description adds value the schema does not: the revenue band triggers an additional revenue-at-stake estimate, which explains why the parameter matters rather than just what it is.

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 concrete verb and resource — returns the Iron/Out UX Score (0–100) for one website — plus the data source (CrUX, last 28 days). The phrase 'for one website' implicitly separates it from the sibling compare_sites without needing to open either schema.

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 a clear trigger ('when the user asks how fast or user-friendly a site is for real visitors') and explicit exclusions (no lab test, no Lighthouse, does not load the site). It does not name compare_sites as the alternative for multi-site comparisons, leaving that inference to the agent.

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