runrunit_share_cursor_skill

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

With no annotations provided, the description carries the full behavioral burden and discloses the key mutation facts: it 'Opens a pull request' in 'one atomic commit' covering the entire folder. It surfaces the auth requirement ('Requires GITHUB_TOKEN on MCP host') and the targeting logic ('repo identity and base branch auto-detected from project_root git origin (env overrides)'). It does not cover failure modes or the response shape, but the core side effects and prerequisites are visible.

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?

Three sentences, each carrying distinct information: purpose and triggers, mechanism and scope, then exclusion and requirements. The multilingual trigger list is somewhat long but earns its place for intent routing, and the critical scoping constraint and exclusion are front-loaded before the less urgent details.

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 two-parameter tool with no annotations and no output schema, the description covers purpose, triggers, exclusions, mechanism, auth, and repo targeting. The main gap is the success response (e.g., PR URL/number) that an agent would need to report back to the user, since no output schema exists to fill that role.

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 100%, so both parameters are already documented and the baseline of 3 is met. The description adds meaning by defining what skill_name maps to — the 'cursor-skills/{skill_name}/ folder (SKILL.md, rules/, templates/, scripts/, etc.)' — and by explaining that project_root drives 'repo identity and base branch' detection, which the schema does not state.

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 opens with 'Primary tool when the user wants to share a Cursor skill with the team via GitHub' and specifies the exact mechanism: 'Opens a pull request that adds or updates the full cursor-skills/{skill_name}/ folder ... in one atomic commit.' It also names the sibling it is not ('Do not use runrunit_install_cursor_skills'), and the 'via GitHub' qualifier separates it from the Bitbucket variants in the sibling list.

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?

Explicit trigger phrases in both Portuguese and English ('compartilhar skill', 'dividir com o time', 'share skill with the team', 'open a PR for teammates') tell an agent exactly when this tool is the right call. It gives a direct exclusion with rationale: 'Do not use runrunit_install_cursor_skills for this — that only copies folders to local ~/.cursor/skills.' The 'via GitHub' framing implicitly routes GitHub users here versus the Bitbucket siblings.

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