report_not_junk

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

With no annotations, the description carries the burden and does it well: it discloses persistent side effects (filter training, addition to a safe senders list) and the default mutation (moving mail to the inbox). It leaves out whether the safe-sender addition is reversible or what happens on partial failure, which keeps it short of 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?

Effects are front-loaded in the first sentence, then guardrails, so nothing important is buried. The trailing quoted instruction is slightly awkwardly formatted but every clause adds information.

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?

Covers the destructive-ish behavior and safety guardrail well for a three-parameter mutation tool with no annotations and no output schema. It still omits what the call returns (e.g., counts of processed messages) and error behavior for mismatched confirm_count, which an agent would want before invoking.

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 description coverage is 0%, so the description must compensate, and it does for two of three parameters: confirm_count is defined as matching the id count with a required confirmation flow, and move_to_inbox's default behavior is spelled out. message_ids is self-explanatory through its name and confirms the batch nature of the call.

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+resource (report messages as not spam) and immediately enumerates the three effects: trains the filter, adds senders to the safe senders list, and moves messages to the inbox. An agent can distinguish this from report_junk or move_messages from the description alone.

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 clear usage constraint — 'Only for senders the user recognises' — plus a hard procedural guardrail to show the user the list first. It never names the obvious alternative (report_junk) for the spam direction, so the when-not is implied rather than explicit.

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