aiworkhub_task_plan_snapshot

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

Annotations already declare readOnlyHint, but the description adds genuine context: default output is deliberately bounded and omits finished cards' dependency history, and the tool has no claiming side effect. It does not discuss cost or size limits of the full mode, which is the main residual gap.

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-loads 'READ-ONLY' and the mode split, then details default-mode contents, then the exclusion. Dense with domain jargon ('write-scope overlaps', 'orphaned processing') but no sentence is wasted.

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 an output schema present and readOnlyHint set, the description needs only to cover modes and side effects, which it does. An agent could call this correctly; only the exact contents/size trade-off of the two modes remains unstated.

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% and the single boolean 'full' is undocumented in the schema, so the description must carry it — and it does, explaining both the default (bounded) and full=true (complete historical DAG) semantics. Only the concrete output differences between the two modes are left somewhat implicit.

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: a read-only 'Plan-DAG summary' with a bounded default mode and a 'complete DAG' mode. The identity is unambiguous as a snapshot/report tool, though it does not explicitly contrast itself with nearby snapshot siblings like roadmap_snapshot or aiworkhub_dashboard_snapshot.

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 tells the agent exactly which mode to pick ('Use full=true for exact historical dependency/layer inspection') and what the default mode is for (actionable lifecycle, ready work, blockers). It also rules out a misuse case by naming the real claim surfaces (aiworkhub_task_auto_pickup / _dryrun).

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