close_issue

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly warns that the tool is DESTRUCTIVE, that the first call is a no-op, and that confirm=true is required for the actual close. This is highly transparent for a mutation tool.

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 concise, front-loaded with the core action, and wastes no words. Every sentence adds meaningful operational 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?

The destructive nature and human-approval flow are well covered, but the tool has six parameters, no annotations, and no parameter descriptions. The description does not explain required inputs like reason or the optional state_reason default. The output schema helps, but parameter semantics remain a notable gap for a destructive operation.

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 only adds meaning for confirm by explaining when it should be true. The other parameters—owner, repo, issue_number, reason, and state_reason—are left with only their bare schema titles. Since coverage is low, the description needed to compensate but did not.

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 states the action clearly: 'Close an issue.' It also adds the critical distinction that the first call only proposes an action and does not actually close anything. It does not explicitly differentiate from sibling tools like reopen_issue or get_issue, so it falls short of full sibling differentiation.

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 provides clear usage context by explaining the two-step confirmation flow: the first call is only a proposal, and the second call with confirm=true should only happen after human approval. It does not explicitly say when to use close_issue versus reopen_issue, but the confirmation protocol is strong guidance.

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