report

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

With no annotations, the description carries the full burden and does well: it discloses the write side effect (saves a snapshot by default), the stateful consequence (moving the window future comparisons are measured from), and the preview escape hatch. It omits return format and any permission/remoteness caveats, which keeps it below a 5.

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?

Two sentences, front-loaded with purpose and then the critical side-effect caveat. The second sentence is dense but every clause (default save, window shift, loop consequence) earns its place.

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-param, no-annotation, no-output-schema tool, the description covers purpose, contents, and the key stateful side effect. An agent can call it correctly; only the exact output shape and remote-server behavior are left implicit.

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 is 3, but the description adds real meaning beyond the schema's terse 'Preview without writing a snapshot' by explaining that no_save affects the comparison window. keep and server remain undocumented in prose, so it is not exhaustive.

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 ('generate') and resource ('butler-style health report') and enumerates its contents (snapshot comparison, warnings, notable changes, suggested actions). This distinguishes it reasonably from generic siblings like system_status or doctor, though it never names those alternatives explicitly.

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 clear operational context for no_save, warning that saving moves the comparison window and that looping leaves nothing to compare against — a genuine when-not-use condition. It stops short of routing the agent to a specific sibling for other use cases.

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