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

Annotations declare readOnlyHint=false, destructiveHint=true and idempotentHint=false, so the safety profile is already carried by structured data. The description adds one genuinely useful behavioral fact — the API key is set out-of-band by a person in the UI, not through this tool — but it never explains what the 'destructive' flag actually means here (e.g. whether omitted fields are cleared or left untouched).

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?

Two tight sentences with no filler, and the parameter semantics are front-loaded ahead of the out-of-band key note. The 'or' phrasing lists three settable things as alternatives, which slightly muddies whether they are independent fields.

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 destructive, non-idempotent, zero-required-parameter mutation with no output schema, the key unanswered question is whether omitting a parameter leaves it unchanged or clears it — the description's 'null: no cap' note hints at explicit clearing but never states the partial-update contract. Annotations cover the raw safety hints, so the gap is moderate rather than severe.

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 only 33% (just 'model' is documented), so the description must compensate — and it does: it explains monthlyCapUsd is in US dollars with null meaning no cap, and clarifies that dailyProposalCap governs training proposals. The model parameter gets no additional treatment beyond the list_ai_models pointer, so it is short of a full 5.

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 enumerates the editable settings (model, monthly USD cap, daily training-proposal cap) but never states the actual action — 'update AI settings' appears only in the title. An agent can infer the mutation from the fields listed, but the phrasing 'Choose the model...' is indirect and does not explicitly contrast with get_ai_settings or list_ai_models, which it only references as a source of ids.

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 usefully tells the agent where the model id comes from (list_ai_models) and that the API key is pasted by a human in Settings → AI, implicitly excluding key management from this tool. It gives no guidance on when to call this versus get_ai_settings, nor on prerequisites or required permission level.

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