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

The annotations declare readOnlyHint=true, but the description says the tool produces folder layouts and starter files for each client and project named — that is a write to the filesystem, directly at odds with the declared read-only behavior. The description does usefully disclose the file set that gets created, but the conflict with the structured safety hint is the dominant signal an agent needs resolved.

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?

One front-loaded sentence naming the layout first and then the concrete artifacts; nothing is padded. The long parenthetical list makes it dense to scan but every item contributes information about the output.

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 a 3-parameter, no-output-schema generator, the description covers what is created but omits where it is created (target directory/root) and what happens to pre-existing files, which matters given all parameters are optional. Idempotency and destructiveness are only conveyed via annotations, and the readOnly hint conflicts with the described behavior.

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 baseline is 3, and the description goes slightly beyond it by indicating that each client and each project name receives its own set of files (STATE, CHANGELOG, TODO, INBOX, CLAUDE.md), not just a folder as the schema text says. It still doesn't say what happens when a name, or business_name, is omitted.

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?

It states a concrete verb (scaffold) and resource (a 'business operating system' folder layout) and enumerates the artifacts produced: CLAUDE.md question/rules files, a wiki layout with raw sources/topics/entities/index/log, plus STATE, CHANGELOG, TODO, INBOX and CLAUDE.md per client and project. That is specific enough to picture the output. It does not, however, distinguish itself from the siblings (daily_routine, house_rules, voice_guide_template), which look like pieces of the same system.

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?

There is no statement of when this tool should be used versus daily_routine, house_rules or voice_guide_template, no note that it is a one-time/initial setup step, and no guidance on whether to call it against an already-scaffolded directory. The only usage cue is implicit in the name 'scaffold'.

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