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

Annotations cover readOnly/destructive/openWorld, but the description adds substantive behavior beyond them: responses are bounded and 'never raw result or logs', legacy task_id returns a status-only envelope, and a completed report task returns a native download next_action. That is genuine disclosure not present in the annotations.

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?

Front-loaded with the primary action, and the terminal-consumption rule is useful, but several sentences are dense with private vocabulary and slightly repetitive around resubmission/refresh semantics. It is longer than it needs to be for three parameters.

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 0% schema coverage, the description carries full burden; it does well on response shape (status-only, next_action at terminal) but leaves connection_context unexplained and does not enumerate the bounded envelope's fields, so an agent still has gaps for a 4-parameter tool.

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% across 4 params, so the description must carry the load. It documents task_ref (opaque ref), task_id (legacy UUID), and response_mode=compact, but connection_context is only obliquely gestured at ('on its original connection/token') and its format/purpose is never explained.

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 concrete verb+resource ('Poll an Agent Method task by opaque task_ref', 'inspect an existing tnapi_ report task_ref') and names the bounded status-only envelope. It is distinguishable from tasks_list/tasks_latest in that it targets a single task by ref, though the heavy private jargon ('bounded common response', 'tnapi_ report task_ref') forces the agent to parse rather than instantly recognize the purpose.

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 real when-to-use guidance: poll by task_ref from insights_query_consistent, do not resubmit the original page-one query at terminal=true, and a later 'check again' starts a new cached query rather than a provider refresh. It does not explicitly contrast against the closest siblings (tasks_list, tasks_latest, tasks_get_create_detail), which is the one missing piece.

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