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

With no annotations present, the description carries the full behavioral burden and does so well: it never mutates tasks in Offhand, never takes work another agent holds, records nudges with a cooldown so agents aren't pinged twice, POSTs to an agent webhook when one is supplied, and returns would_nudge/would_reassign in free watch-only mode. These are exactly the side-effect constraints an agent needs before invoking a tool that triggers nudges.

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 definition is dense but front-loaded: what you feed in and get back comes first, then the stalled/failing semantics, then the ladder, then the Pro/free and safety limits. Every sentence carries behavioral information, though the run-on structure could be tightened into shorter clauses.

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 7-parameter tool with nested objects and no output schema, the description covers the key return information (which tasks are stalled/failing, what to do, would_nudge/would_reassign in free mode) and the mutation boundary. It stops short of describing the response object's structure, which is a noticeable gap given no output schema exists.

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 the baseline is 3, but the description adds conceptual meaning the schema does not: board scopes cooldowns and the escalation ladder, stall_minutes and fail_limit are tied to the stalled/failing definitions, and webhooks are explained as nudge targets. It does not define formats for the nested task fields beyond what the schema says.

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 description opens with a specific verb+resource+scope: pass in the tasks agents handed each other and get back which are stalled/failing plus recommended actions. It is clearly distinct from the siblings (nudge_log, usage_and_upgrade, weekly_report), and it even names the upstream source (Offhand list_todos) and the downstream artifact it returns (an Offhand add_task call).

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 gives concrete definitions of when a task qualifies as stalled (claimed/untouched for stall_minutes) or failing (blocked or fail_limit hits), and describes the escalation ladder and the Pro vs free watch-only split. It never explicitly states when to prefer this over nudge_log or other siblings, so no exclusions are offered, but the operating conditions are unambiguous.

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