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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true), and the description adds genuinely non-obvious behavior: the call only marks viewed/dismissed/acted-upon state with no downstream side effect, plus retry semantics via idempotency_key. The retry-safe claim sits in slight tension with idempotentHint=false, but that is a nuance (key-based dedup vs. inherent idempotency) rather than a contradiction.

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 tight sentences with the purpose front-loaded, followed by required inputs and then retry semantics. No filler; every sentence contributes a distinct fact an agent needs.

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 state-mutating tool with no output schema, the description covers purpose, required inputs, the no-side-effect caveat, and idempotency behavior. The only real gap is the shape of a successful (non-retry) response, which is left unstated since no output schema exists to carry it.

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 71%, so the schema carries much of the load, but the description still adds meaning: it names insightId and action together as the operative inputs and explains what each enum value does to recorded state. It also documents idempotency_key behavior (repeat call returns original result), which the schema only exposes as a pattern/example.

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 verb and resource ('Update the recorded state of an analytics insight in workspace_id') and scopes it to workspace_id. It also draws a sharp line against the read/generate siblings by clarifying it only records state and does not carry out the recommendation. An agent can distinguish it from aidelly_get_analytics_insights and aidelly_generate_analytics_insights without opening a 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 tells the agent what must be supplied ('insightId and action') and hints at a boundary ('it does not carry out the recommendation itself'), which implies when-not-to-use. However, it never names the alternative tool an agent should reach for when it actually wants to act on a recommendation, so the guidance is implied rather than explicit.

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