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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety bar is low. The description adds genuinely new behavior: the link is one-time, approval happens out-of-band by the user, and tools appear only after reconnection — all of which the annotation block does not convey.

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 short sentences in causal order — what you get, what happens after approval, what to do first. Zero filler and the key guardrail is front-loaded enough to be acted on.

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 only one required parameter, a rich enum schema, an output schema, and annotations covering the safety profile, the remaining burden on the description is the user-facing workflow — which it covers end to end (request, user approval, reconnection, new tools).

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 100% and the tiers enum is fully enumerated in the schema, with the schema itself carrying the 'never choose for them' instruction. The description only echoes that instruction ('ask the user which tiers first') and adds no syntax, defaults, or tier-combination meaning, so baseline 3 applies.

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?

Names a concrete artifact ('a one-time link') and the exact outcome ('the app reconnects and the new tools appear'), which is far more than a restatement of the name. It does not explicitly contrast with adjacent siblings like list_granted_scopes or search_tools, so an agent must infer that this is the escalation path rather than the inspection path.

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?

'Ask the user which tiers first' is an explicit procedural precondition, and the reconnect flow tells the agent the context in which this applies. There is no explicit when-not guidance (e.g. check list_granted_scopes before requesting), so it stops short of a full routing rule.

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