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

Far beyond the single readOnlyHint annotation, the description discloses the polling strategy (exponential backoff, 2s initial, 1.5x, 30s max, jitter), the terminal states and their meaning, the timeout behavior ('status "pending"', re-call with same id), and the auth requirement. This is exactly the operational context an agent needs before committing to a long-poll.

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 and backoff are front-loaded in the first two sentences, followed by clearly separated 'Agent usage' and rendering guidance. It is long (four paragraphs) and the 'user does not see tool results' point is restated, but nearly every sentence carries actionable instruction rather than filler.

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 no output schema and only a readOnlyHint annotation, the description carries the full burden and does so: it covers sequencing, terminal states, timeout/resume behavior, authentication, and the cross-tool rendering step with render_auth_link. An agent can drive the whole 2FA flow from this text.

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 both session_id and timeout_seconds (default, max, client-timeout interaction, re-call semantics) are already documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 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?

The first sentence states a specific verb and resource ('Poll a 2FA session until the user completes the challenge'), which cleanly separates it from status-readers like get_2fa_status and verifiers like verify_2fa. An agent knows exactly what operation this performs without opening the 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 explicitly names the prerequisite ('Call this after start_2fa with the returned session_id'), the terminal states and the follow-up action for each ('expired' → restart with start_2fa), plus an access caveat ('start_login does NOT open this tool'). What's missing is any routing against the non-blocking alternative get_2fa_status for an agent that doesn't want to wait.

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