Create a GitHub issue

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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true) by disclosing partial-failure semantics: after creation, a failed kind/parent/blocked_by step is reported in errors while the issue is still returned. It also warns that a missing milestone fails before the issue is made, that a type:<kind> label is created when missing, and that assignees are notified — all behavioral traits the structured fields do not convey.

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?

Roughly three dense sentences with no filler, and the scope statement is front-loaded ahead of the edge-case behavior. The reference-format sentence is compact but packs several parameters into prose rather than structure, which costs a little scannability.

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?

With an output schema present, the description need not explain return values, and it correctly focuses on the non-obvious parts: partial success, the milestone precondition, and reference formats. For a 10-parameter write tool with broad side effects, an agent has everything needed to call it correctly.

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 100%, so 3 is the baseline, but the description adds real meaning: the kind fallback resolution order (Issue Type, else a created type:<kind> label) and the accepted issue-reference grammar (12, #12, owner/repo#12, URL), including that a bare number resolves against the new issue's repository. These are resolution rules rather than restatements of the schema text.

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 and resource ('Create an issue in a repository') and immediately scopes what can be settled in the same call: kind, labels, assignees, milestone, parent, blocked-by. This clearly separates it from the sibling set (close, reopen, relate, develop, read, edit, comment), all of which operate on existing issues.

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 an explicit precondition ('a repository the viewer may write to') and explains the failure/success contract, including that a missing milestone aborts before creation unless create_milestone is true. It never names an alternative tool explicitly, but the create-vs-edit boundary is unambiguous from the verb, so this is clear context without exclusions.

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