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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine domain behavior the annotations cannot: that erased messages and their files disappear within the hour, and that null is the default meaning 'as long as the company is'. It stops short of describing response format or whether both fields are always present.

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?

The first clause front-loads what is measured, and each following clause (legal values, erasure timing, mutability) is load-bearing. The quoted-key style and em-dashes make it slightly dense to parse, but no sentence is wasted.

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?

With no parameters and no output schema, the description carries the entire explanatory burden and does so: it defines both returned fields, the default, the allowed values, and the deletion consequence. An agent can report the retention setting to a user from the description alone.

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?

There are zero input parameters, so there is nothing for the description to disambiguate. It does spend its words explaining the returned fields ('days' and 'mayChange'), which is a useful substitute given no output schema exists.

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 description states a specific resource and its exact semantics: chat retention, with the three legal 'days' values (30/90/365) plus null meaning indefinite. It also names the sibling that mutates this state, so the tool is distinguishable from set_chat_keeping without opening either 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?

It routes the mutation case explicitly: 'the company's owner only, with set_chat_keeping', which tells the agent when this read tool is insufficient and which sibling to use instead. It doesn't spell out read-side preconditions, but that is minor for a no-arg getter.

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