review_story

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

With no annotations, the description carries the full burden, and it delivers: it discloses the concrete side effects (opens PR via gh, sets status to pr_open or changes_requested), explicitly states it does not merge, and explains no-op behavior for invalid statuses. This is strong behavioral disclosure.

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 tightly packed paragraphs that front-load the main behavior, then add the critical precondition and exclusion. Every sentence adds usable information with no filler.

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?

For a tool with an output schema, the description covers the essential call-time facts: action, status transitions, non-merge guarantee, and invalid-call handling. It also references the README for deeper review/merge detail, so an agent has enough to invoke it safely.

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% and the description does not define plan_name or story_key beyond their names. The general story/status context helps indirectly, but the required parameters are left mostly 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 and resource: running the code-reviewer persona over a dispatched story's branch. It clearly distinguishes itself from merge-related siblings by explicitly saying 'Does not merge — merge is the overlord's decision.'

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?

Gives an explicit precondition: only reviewable when story status is 'tests_passed', and any other status is a no-op skip. It even anticipates stale/duplicate racing calls and points to README for more context, making when-to-use versus when-to-avoid unmistakable.

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