runrunit_create_pr_github

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

With no annotations, the description carries the full burden and does so well: it discloses the no-op default, the exact approval gate for the mutating path, the protected-branch prohibition, and the post-execution response fields (pull_request_url, branch, target_environment). Side-effect boundaries are clear.

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?

A dense but efficient paragraph with zero filler; the plan/execute distinction and branch constraints are front-loaded before secondary details. Every clause carries actionable information.

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 12-parameter mutation tool with no annotations and no output schema, the description covers the safety profile, approval workflow, and response shape. Nothing an agent needs to call it correctly appears missing.

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 already 92%, so the schema documents most parameters (base enum, approved default, project_root path semantics). The description adds a meaningful protocol layer on approved ('only after the user accepts...') beyond the schema's field-level note, but does not re-explain the remaining fields.

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 ('Plans or opens one GitHub pull request') and its scope ('to development or homolog, never main or master'), which distinguishes it from siblings like check_pr and commits_branches_prs. An agent can tell what it does and its target constraints without opening the schema.

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 explicit operating conditions: default is plan with no push or gh pr create, and approved:true should be passed 'only after the user accepts title, body, base, and branch.' It also excludes out-of-scope actions (Runrun.it comments, screenshots), routing them to follow-ups.

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