get_stuck_work

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the exact data categories returned and the scoping options, but says nothing about read-only safety, authorization needs, or result size/volume, which the agent would want before invoking it.

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 purpose is front-loaded and the second sentence handles scoping; there is no filler. The first sentence is a dense colon-list run-on, but each enumerated item is load-bearing because it defines the tool's scope.

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, no annotations, and 0% schema description coverage, the description should ideally sketch the response shape and explain as_agent. It covers the content categories and plan scoping well but leaves those gaps for an agent trying to call it correctly.

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 0%, so the description must compensate. 'Scoped to a single plan or global' effectively explains PlanId (omit to go global), but the as_agent parameter is never mentioned, leaving one of two parameters entirely opaque.

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 (view) and resource (stuck work) and then defines exactly what 'stuck' means: tasks past TTL, findings in pending_verification >24h, attempts past TTL, plans with no recent events. That enumeration cleanly separates it from siblings like get_my_active_work or get_plan_dashboard.

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?

'On-demand view of the same data the hourly stuck-work job computes' tells the agent this is the manual counterpart to an automatic job, which is clear usage context. It does not name an alternative tool or state when not to use it, so it falls short of explicit routing guidance.

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