How to write a Tourwright script

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

Annotations already declare readOnlyHint, idempotentHint and closed-world behavior, so the agent knows this is a side-effect-free read. The description adds that the payload is documentation content (format, actions, voices, examples) but says nothing about size, structure, or whether it returns one document or sections — modest added value against the already-covered safety profile.

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?

A single sentence with the content summary front-loaded and the call-to-action at the end; nothing is redundant. The middle list ('every action, voices and examples') is slightly compressed and would read better as a clearer enumeration, but no filler is present.

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 parameters, no output schema and no nested structures, the description carries most of the burden and does state what content comes back. It stops short of describing the document's shape or length, which would help an agent budget reading it, but nothing needed to invoke 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?

Zero parameters, so the baseline applies; there is no input semantics left for the description to carry. The one sentence is consistent with an argument-free fetch.

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 names the resource plainly: the Tourwright script format, covering browser walkthroughs, narrated slides, actions, voices and examples. An agent can tell this is a reference/guide fetch rather than an action tool, though it does not state a verb and overlaps thematically with the sibling tourwright_voices, leaving mild ambiguity about which one to open for voice details.

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?

'Read it before writing a script' gives an explicit precondition that selects this tool over the action siblings (validate, render, job). It does not name any exclusions or point to the follow-on siblings such as tourwright_validate for the step after reading, so guidance is clear but not complete.

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