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

With no annotations, the description carries the full behavioral burden. It adds useful context about return values and the authentication prerequisite, but leaves a critical polling behavior unspecified: what happens if the user has not interacted yet (error, empty result, retry guidance). It also never states whether the operation is read-only, leaving the safety profile unstated.

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?

Two tight paragraphs with the main action and return values front-loaded. The ACCESS paragraph earns its place with concrete authentication instructions and a relevant exclusion. Slightly dense but no wasted 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?

Reasonable for a single-parameter tool: purpose, returns, and auth precondition are covered. However, without an output schema, the description should clarify poll termination semantics (timeout, repeated-call behavior, non-interaction response) and the relationship to wait_for_chat_id_discovery for an agent to use it reliably.

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%; the token parameter is already documented in the schema as 'Discovery token from create_chat_id_discovery,' which is sufficient. The tool description adds no additional parameter semantics beyond the schema, so the baseline of 3 is appropriate.

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?

Uses a specific verb ('Poll') with a clear resource (a chat ID discovery token) and states the return values (Telegram chat ID, user ID, username once the user interacts). It distinguishes itself from start_login with an explicit 'does NOT open this tool' note, though it does not differentiate from the closely related sibling wait_for_chat_id_discovery.

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?

Provides clear when-to-use context: requires a Proof account, must authenticate first, and the tool should be called after obtaining a discovery token. It also gives an explicit when-not signal ('start_login does NOT open this tool'). However, it does not articulate the choice between this polling tool and the wait_for_chat_id_discovery sibling.

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