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

Annotations declare write, openWorld, idempotent, non-destructive; the description is consistent and adds real value beyond them: the collection is created or reused (explaining the idempotent hint) and a pasted secret key is stored encrypted and never shown again. That secret-handling and interaction constraint is exactly the kind of context annotations cannot convey. It stops short of describing failure modes or what a successful response contains.

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?

Dense and front-loaded: the core action and its effects come first, then input sourcing, then the secret-handling caveat. Phrasing is terse to the point of being clipped ('inputs = the keys list_apps shows'), which costs a little readability but wastes no sentences.

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 5-parameter write tool with a nested inputs object, annotations, and no output schema, the description covers the prerequisite, side effects, idempotency, and the sensitive-input rule. Remaining gaps (behavior on invalid keys, whether name overrides the collection name) are mostly covered by the schema, so nothing critical is missing for a correct call.

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 100%, so the schema already documents id, app, name, inputs, and bookingUrl. The description clarifies that 'inputs' keys mirror what list_apps shows and that values in it may be pasted secrets, which adds some meaning, but it does not explain name or bookingUrl at all. Baseline 3 is appropriate when the schema does the heavy lifting.

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 ('Connect an app') and goes further to name the two effects: it makes or reuses the app's collection and runs the first sync. Tying the app identifier to list_apps makes the relationship with that sibling explicit, so an agent can tell which tool to call first.

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?

Clearly establishes the prerequisite ('from list_apps') and constrains interaction behavior ('never ask for one they haven't offered, point them to the hint'). It gives clear context for when to use it, but never names the alternative for a subsequent re-sync (sync_collection) or states when not to use it.

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