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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value by enumerating what comes back (applicable modules, next tool, five rules, prioritized rules), which matters since there is no output schema. It stops short of explaining how modules are matched or what happens if the task string is vague or omitted.

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 imperative trigger before the return-value inventory, and the example list is compact and purposeful. The single long sentence is dense but each clause conveys routing or output information, so there is little waste.

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 one-parameter, read-only router with no output schema, the description covers the trigger, the return contents, and the follow-on tooling. The only gap is behavior when the task argument is absent or too vague, which is a minor omission for this complexity level.

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% and the single parameter is already documented with its own examples, so the description need not repeat format details. It reinforces that the input is a sentence describing the assignment but adds no new syntax or constraints beyond the schema, making the baseline 3 appropriate.

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 action and trigger ('call this at the START of any task') plus the concrete return payload: which ihumane modules apply, the next start tool to call, the five rules, and task-relevant rules. It also names the downstream categories (UI design, Code craft, Product thinking, Copy) that correspond to sibling tools, so an agent can place it as the entry-point dispatcher.

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 strong trigger condition — the start of any task — backed by concrete task examples spanning page, feature, bug fix, product idea, database change, and document. It does not state exclusions or describe when to skip it and go straight to a specific sibling start tool, which keeps it short of a 5.

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