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

The description adds substantial detail beyond what annotations already convey: it writes to the customer's GitHub repo, never the site; it requires a preview-then-confirm flow; it is idempotent with a pattern-skip behavior; it refuses to exceed the site issue cap; and it demands a PRO plan. This is exactly the side-effect, confirmation, and failure-mode transparency an agent needs for a destructive write.

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 long and uses several ALL-CAPS phrases, but every sentence carries a distinct operational fact (purpose, issue payload, side effect, prerequisite, confirmation, idempotency, cap, plan). The core purpose is front-loaded, and the dense formatting is justified by the high-risk nature of the tool.

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 destructive write tool with no output schema, the description covers all needed context: how issues are aggregated, what content each issue carries, where the repo comes from, confirmation token mechanics, token expiry, idempotency, cap enforcement, and plan prerequisite. An agent can safely invoke this tool correctly from the text alone.

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%; the input schema already fully explains 'website' and the confirm-preview-token flow. The description does reinforce the confirm semantics and adds that the repository is sourced from set_github_repo, but it does not need to add new semantics for the parameters since the schema covers them—baseline for covered params is therefore a 3.

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 names a specific action (file findings as GitHub issues) and resource (customer's GitHub repo), then refines the scope by defining a 'pattern' so an agent can predict exact issue granularity. It also distinguishes itself from every sibling by flagging that no other tool writes to the repository, so there is no ambiguity about which tool to choose.

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?

It gives a clear context: run after a scan to turn findings into issues an agent can act on, and it names a prerequisite (set_github_repo) that must be called first with 'this will not choose one.' It does not explicitly name sibling tools like validate_fix or list_violations as alternatives, but its side-effect exclusivity claim still guides selection.

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