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

Annotations only mark readOnlyHint=true; the description adds that results are judged on sent mail rather than what arrived, and that the default six-month cutoff is the corpus dormancy line rather than a tuned threshold. This gives meaningful behavioral context beyond structured annotations.

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?

Three sentences, all informative: output shape, use cases, data source, and default semantics. No filler; the most important functional information appears first.

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 simple read-only tool with two optional documented parameters and no output schema, the description covers what is returned, the ordering, the basis, applicable contexts, and the meaning of the main parameter. Nothing necessary for correct invocation 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?

Parameter schema already covers both params at 100%, so baseline is 3. The description adds value by explaining that days 'sets the line' and its default corresponds to the corpus's dormancy line, which the schema alone does not convey.

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?

Description states the tool returns people the user has not written to in a while, ordered quietest first, with the date of their last sent item. It also distinguishes this from ranking who is worth contacting, so an agent can tell it apart from related sibling tools.

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?

Explicitly says 'Use when a skill needs to know who has gone quiet rather than to rank who is worth contacting' and gives concrete cases: drifted clients, overdue notes, silence since a given point. This is strong when/when-not guidance, even without naming a sibling.

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