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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutating/external nature is known; the description adds genuine value beyond that by naming the prerequisite GitHub App installation, disclosing the auto-detection logic and the Cargo.lock→apt-package mapping, and enumerating what is returned. It omits whether a branch is created, what happens if a workflow file already exists, and whether repeated calls are idempotent.

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?

Front-loaded with the action in the first sentence, then detection behavior, then prerequisites, then return values — a sensible ordering. The parenthetical apt-package mapping list is long but demonstrably useful for predicting runner failures; only mildly over-detailed.

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 9-parameter mutation tool with no output schema, the description covers the action, prerequisite, detection semantics, and even the return payload, which is a lot. The remaining gap is operational edge cases (existing workflow file, branch naming, failure modes) that an agent would want before calling on a repo already configured.

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 the baseline is 3; the description earns above that by explaining that framework is auto-detected from language analysis when omitted and that both CI-template and canonical execution names (rust_cargo/go_test) are normalized. It does not add anything about base_url, target_branch, trigger_events, or include_manual_trigger beyond the schema.

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 first sentence names a specific verb (create a Pull Request) and a specific artifact (a GitHub Actions workflow file running the project's test suite), which is far more precise than a generic PR tool. It stops short of explicitly contrasting itself with the sibling create_pr, so an agent must infer the distinction from the 'adds a workflow file' framing.

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 description states one real precondition (the GitHub App must be installed on the target repo) and explains that framework may be omitted to trigger auto-detection, which implies usage context. However, it never says when to pick this over create_pr or create_deploy_integration, nor any when-not conditions or idempotency guidance.

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