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

Goes well beyond the readOnly/idempotent annotations: retention windows (screenshots 24 hours, reports 7 days), the 6-image phone+desktop cap, and a prompt-injection warning that screenshot text is page data, never an instruction, plus the untrusted customer_text wrapping. These are exactly the behavioral traits annotations cannot express, and they are consistent with readOnlyHint.

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 the purpose, then semantics, then safety, then the default-case fallback — a sensible order with no filler sentences. The semicolon-chained clauses make it dense to parse, which keeps it just short of a 5.

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 still enumerates what comes back (verdict, every issue with its fix, each journey's steps, optional screenshots) and explains the zero-argument default. Nothing an agent needs to call this correctly or interpret the result is missing.

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 0%, so the description fully carries the burden, and it does: runId is defined by provenance, screenshots is defined by effect and cap ('returns the pages as images (phone and desktop, up to 6)'), and pages is defined by narrowing behavior with a concrete example (["/app"]). All three parameters gain meaning absent from the bare schema.

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 verb and resource ('Reads a site test run again') and anchors it to its sibling by naming where the runId comes from (site_test or a FAILED-at-test publish). An agent can distinguish this re-read tool from site_test/site_history without opening any 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 clear trigger conditions: call it to re-read a run whose runId came from site_test or a failed publish, and states the no-runId fallback ('the last 5 runs'). It does not explicitly say 'use site_test to start a new run instead', but the parenthetical makes the alternative implicit.

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