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

With annotations present the bar is lower, and the description still adds real context: authorization requirements, retry semantics, and the explicit non-effect on bounty outcome. The retry-is-safe wording sits slightly at odds with idempotentHint=false, but this reads as scoping one field rather than a flat contradiction.

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 short sentences, effect first, then permission, then edge-case semantics. No filler and nothing buried.

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-required-param mutation with no output schema, the description covers side effects and auth but leaves the identifier semantics and the outcome of a successful call (what a dispute object looks like) unexplained. Adequate, not complete.

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 0% and neither parameter is named in the description. 'id' is genuinely ambiguous — artifact id, submission id, or bounty id — and 'reason' has a 2000-char cap that the description never hints at (what counts as a valid reason, whether it is user-visible).

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 a concrete effect (opening a dispute pauses file cleanup) rather than restating the name, so the agent knows what the call accomplishes. It does not explicitly contrast itself with the sibling resolve_artifact_dispute, leaving the open/close pair to be inferred from names.

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 an eligibility gate (owner or granted participant) and clarifies retry behavior, which are useful invocation conditions. It never says when to prefer this over resolve_artifact_dispute or what prerequisites (e.g., an existing submission) must hold before opening a dispute.

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