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

Annotations only cover idempotency and the non-destructive/not-read-only profile; the description adds substantial behavior the agent could not otherwise know: existing token scopes are preserved, dependencies are auto-included, granted scopes bypass the prompt, refusal conditions, the host-opened Binder consent flow, and the subtle note that a successful retry does not imply no consent prompt appeared.

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 core action is front-loaded and most sentences carry procedural value (prerequisites, edge cases, retry). However, the Binder consent sentence ('The person can choose project/account access... Accounts appears with requested and selected resources:read or resources:write') is dense and somewhat ambiguous, and one or two sentences could be tightened.

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 one-parameter, consent-triggering tool with no output schema, the description covers the full workflow: prerequisites, refusal behavior, preservation of existing scopes, and the required retry-and-reread loop. Return-value details are not given, but with no output schema the description adequately tells the agent how to proceed after invocation.

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 0%, so the description must carry the load; it partially does by explaining that scopes should come from get_capabilities' 'requestable' list and that required dependencies are added automatically. The 14-value enum is self-documenting, but the description doesn't clarify the read/write semantics of individual scopes beyond a passing 'resources:read or resources:write' reference.

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 ('Prompt the person to authorize missing permissions on this connection') and explicitly bounds the scope of the action ('without creating or editing items'). It also routes to the sibling get_capabilities, so an agent can distinguish it from data-mutation tools like item_create or association_save.

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?

Gives explicit prerequisites and sequencing: 'First read get_capabilities and request only scopes in requestable that the person's task needs.' It also states edge-case outcomes (already-granted scopes succeed without a prompt; ungrantable permissions are refused) and the post-approval step ('retry and read get_capabilities again'), leaving little to inference.

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