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

Annotations cover the safety profile (readOnlyHint), so the bar is lower. The description adds real behavioral context beyond that: ordering, that it returns the latest contact date, and an explicit coverage limitation to 'covered connected sources and imported metadata'.

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 core definition, then caveat, then coverage, then the one parameter note. Every sentence earns its place with no redundancy.

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?

Though there is no output schema, the description conveys what is returned (people, ordering, latest contact date) and flags the data-coverage limitation. Combined with the readOnly annotation and full schema docs, nothing needed 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?

Schema coverage is 100%, so both parameters are already documented with defaults. The description's note that 'days sets the threshold; the default is six months' restates the schema default of 182 rather than adding syntax or edge-case meaning, which matches the baseline 3.

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 resource (people with no recorded contact in either direction) plus ordering (quietest first) and returned content (latest contact date). An agent can distinguish this from neighbors like top_message_correspondents, what_needs_attention, or job_changes without opening the schema.

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 when to use it ('for relationships that have gone quiet') and adds a disambiguating caveat that it is not a ranking of who is worth contacting. It stops short of naming an alternative sibling tool for a different question, so it is not a full 5.

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