get_plan_dashboard

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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its words elsewhere: it discloses in-process caching for 5 seconds and invalidation via LISTEN/NOTIFY, which is real staleness information an agent cannot get from annotations. It does not mention the caller-identity behavior of `as_agent`, which is the one behavioral 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?

Two dense sentences, front-loaded with the payload inventory, then the orchestration use case, then caching semantics. No filler and nothing repeated from annotations or schema.

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, the description correctly enumerates return contents and their bounds (up to 5 tasks, 20 events), which is exactly what an agent needs to plan around. The remaining hole is `as_agent` semantics and what the stuck-work threshold means operationally for any non-default caller identity.

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% for two parameters, so the description must compensate — and it does not. `PlanId` is inferable from context, but `as_agent` is a semantically loaded parameter (whose claims are reported as 'the caller's'?) that is completely unexplained 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 ('Comprehensive snapshot for one plan') and enumerates exactly what the snapshot contains (per-status counts, per-phase counts, next-claimable tasks, held claims, stuck work, recent events). This sharply distinguishes it from siblings like get_stuck_work, get_event_log, and get_my_active_work, which each return a subset.

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?

'This is the single call an orchestrator makes every iteration to decide what to do next' gives clear usage context and implicitly tells the agent to prefer this over assembling the picture from the narrower sibling tools. It stops short of explicitly naming those alternatives or stating when NOT to use it (e.g., when only recent events are needed, use get_event_log).

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