list_allowed_roots

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely useful context beyond that: it explicitly states it executes nothing ('only reads the configuration and lists directories') and documents the return shape, including that a friendly-named project appears as { path, name } and that the name is passable as cwd.

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?

The payload is dense but front-loaded: what it returns comes first, usage second, behavioral caveat third, return-shape note last. Every clause carries information, though the sentence count and parenthetical environment-variable references make it denser than strictly necessary.

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?

There is no output schema and no parameters, so the description carries the whole disclosure burden — and it does, covering return contents, the { path, name } shape, the glob handling of extra roots, the cross-root flag, and the non-executing guarantee. Nothing an agent needs to call 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?

The tool takes zero parameters, so the baseline is 4. The description still usefully explains how a value surfaced by this tool (a project 'name') is later consumed as a 'cwd' argument, adding cross-tool semantic value.

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 specific verb and resource — returns the server's allowed-roots configuration — and enumerates exactly what that comprises (primary project, registered roots with globs, existing projects, cross-root flag). An agent immediately knows what it gets back. It does not explicitly differentiate itself from the similarly-scoped sibling `resolve_cwd`, which keeps it just short of a 5.

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?

Usage is stated as a direct trigger: 'Use THIS tool whenever you need to find out whether — and with which cwd parameter — you can run a command in another project.' That is a clear when-to-use condition with a behavioral contrast ('runs no commands'). No alternative tool is named for the same need, so no exclusion clause exists.

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