get_stuck_work

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so safety is covered. The description adds real value beyond that by defining the exact semantics of 'stuck' (five concrete detection rules) and noting the data mirrors an hourly batch job, so an agent knows it is a read-only reconstruction rather than fresh state mutation. It does not mention cost or result size for a global scan.

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?

One front-loaded sentence that names the mechanism, then a compact enumeration of the detection categories, then the scoping clause. No filler and no repetition of the tool name or annotations.

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% parameter coverage, the description does its job of explaining what kinds of records come back, but an agent still cannot tell what 'as_agent' does or whether the response is grouped per category. Adequate for the return-content question, incomplete for invocation details.

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%, so the description must carry all parameter meaning. 'Scoped to a single plan or global' implicitly explains PlanId (omit it for global), but 'as_agent' is never mentioned at all, leaving a likely impersonation/identity parameter completely undefined in both schema and description.

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+resource ('on-demand view of ... stuck-work') and enumerates the five detection categories (TTL-expired tasks, over-long claims, stale pending_verification findings, expired attempts, silent plans), which tells an agent exactly what data it returns. It does not, however, distinguish itself from near-neighbors like get_plan_dashboard or get_my_active_work, which also surface work state.

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?

'Scoped to a single plan or global' implies the two usage modes, and 'on-demand view of the same data the hourly job computes' implies it is for checking current state without waiting for the hourly job. But there is no explicit guidance on when to prefer this over get_plan_dashboard / get_my_active_work, and no prerequisites or exclusions are given.

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