get_stale_relationships

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

readOnlyHint=true already tells the agent this is a safe read, so the description's job is to add context — and it does define staleness as based on interaction recency while excluding non-ordinary interactions. However, it never says what counts as an 'ordinary' interaction, how ordering works, or how many results come back relative to the limit.

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?

A single front-loaded sentence with no filler or redundancy. It is tight, though the brevity comes partly at the cost of the missing parameter and scope detail noted elsewhere.

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 three-parameter filtering tool with no output schema and only a readOnly annotation, the description leaves the key unknowns (meaning of category, units of threshold_days, cap from limit) entirely unaddressed. The agent would have to guess at parameters that materially change the result set.

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 carry the burden for limit, category, and threshold_days, and it mentions none of them. 'Recently' only loosely gestures at threshold_days and gives no units or default, while category and limit receive no explanation at all.

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?

The verb 'Return' plus the resource 'people' and the qualifier 'not interacted with recently' make the operation identifiable and distinct from siblings like search_people or get_person_timeline. The trailing clause 'using ordinary interactions only' is a scoping detail but its meaning is never defined, leaving a small ambiguity.

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?

There is no guidance on when to call this instead of alternatives such as search_people, get_person_timeline, or get_relationship_graph. The only usage-adjacent hint is the exclusion of non-ordinary interactions, which is itself unexplained.

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