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

Beyond the annotations (which only say non-read-only, open-world, non-destructive), it discloses the trust model (no cookies or password are exposed), that the user must be shown a link and user_prompt, and that a 'connected' status yields an opaque session handle for alterlab_task_start. It stops short of covering failure/expiry paths, timeouts, or consent revocation, so it is strong but not complete.

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 tight sentences, front-loaded with the purpose, then the start path, then the poll path and alternatives. Every clause carries routing or behavioral information, and the sibling references are anchored to concrete conditions.

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, the description does the work of describing what start returns (link, user_prompt, connect_id) and what poll returns on success. It omits the non-connected statuses an agent will actually encounter while polling and does not say how long consent stays valid, which is a real gap for a polling workflow.

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%, so the baseline is 3, but the description adds meaning the schema cannot: the parameters form two mutually exclusive modes and the connect_id returned by a start is the input to a subsequent poll, with the resulting session handle feeding alterlab_task_start. It does not add format or validation detail beyond the schema, which the schema already handles.

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 pair and resource ('Start or poll a connect request') plus the outcome ('act on a site as the user without ever seeing their cookies or password'). It also names the two modes and explicitly contrasts itself with alterlab_task_start and alterlab_scrape, so an agent can place it 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?

Gives explicit when-to-use ('Use before alterlab_task_start'), an explicit when-not/alternative ('for a page that needs no login use alterlab_scrape'), and routing rules for the two modes (pass site to start, connect_id to poll). Nothing about selection is left to inference.

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