Check a script and propose fixes

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

Goes well beyond the supplied annotations by describing the return payload (failed steps with the target looked for, the page, and the targets that page offers, plus a guessed new target) and the conditional `fixed` field that only appears for YAML text input. Annotations already cover safety and idempotency, so this is added context rather than a load-bearing gap-fill; it stops short of saying whether the run has side effects on the live site or what it costs in latency.

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-loads the action and the validate contrast, then the return shape, then the workflow placement — a sensible ordering with no filler sentences. The middle sentence is long and parenthesis-heavy, which costs a little readability for an agent skimming.

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 carries the burden of explaining returns, and it does so for both the failure list and the `fixed` field. Minor gaps remain around how `vars` interacts with the check and how large a script it can handle, but nothing essential to invoking it correctly 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 coverage is 100%, so the baseline would be 3, but the description adds genuinely new semantics: it explains that the text form of `script` yields the `fixed` rewrite while the object form does not, which disambiguates the anyOf branch in a way the schema does not. The `vars` parameter is left entirely to the 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 — run a script against the real site, fast, without voice or video — and explicitly contrasts it with the sibling validate tool, which "only checks its structure." An agent can distinguish this from tourwright_validate and tourwright_render 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 an explicit sequencing rule: "Use it after the site changed, then validate and render." That names both alternatives and the condition that selects them, so the agent knows where this sits in the workflow rather than inferring it.

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