summary

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the summary is built from the hook's records and returns both `text` and a ready `card`, and it clarifies that launching auto/ask steps is the agent's downstream action, not a mutation by this tool. It stops short of describing filtering behavior or failure modes.

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 description is a single dense run-on containing parentheticals, Russian text, and an emoji anchor marker. The purpose is buried behind the trigger condition rather than front-loaded, and the instruction payload would be clearer as separate sentences; it is over-packed rather than economical.

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 partially compensates by naming the returned `text` and `card` and their contents (verdicts, lost agents, PRs, CI). But parameters are left entirely to the schema and the behavior of the queue/repos/stale inputs is never tied back to the output, leaving the picture incomplete for a tool whose returns are undocumented.

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% with all four parameters (queue, repos, stale, session) documented in the schema itself. The description adds nothing about those parameters, so baseline 3 applies.

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 does reveal that the tool produces a summary assembled by code from hook records plus a `card` (AskUserQuestion input), but it opens with a trigger condition ('When no subagent is left') rather than a clean verb+resource statement. It is distinguishable from siblings only indirectly, and the mix of purpose with post-call instructions makes the core function fuzzy.

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?

The condition 'When no subagent is left' gives an implied trigger for calling the tool, which is useful. However, it never names or contrasts with the sibling tools (source_text, verify_report, snap), and the rest of the sentence is guidance about what to do with the output rather than when to choose this tool.

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