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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description goes further by explaining the blast radius — the new text replaces the whole README, not a merge. It does not mention required scopes/permissions, which is a minor gap for a write operation.

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?

Four sentences, each carrying information, with the action and its destructive scope front-loaded. Slightly verbose around the Studio explanation, which is helpful context but not strictly necessary.

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 with an output schema available, the description covers purpose, scope of replacement, and preparation, so an agent can call it correctly. Missing auth/permission expectations and any note on variant validity keep it from a 5.

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 only 33% (just the readme field); graphId and variant have no schema descriptions. The description partially compensates by naming all three inputs and clarifying the README must be the full text, but it adds no format or identifier semantics for graphId/variant.

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 opens with a specific verb+resource ('Replace the README of a graph variant') and anchors it to a known CLI operation, so the agent knows exactly what side effect this tool performs. It is clearly distinguishable from the read-only sibling GetReadme.

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 concrete preparatory guidance ('read the current one with GetReadme first if you intend to keep any of it'), which is genuinely actionable. It doesn't state explicit when-not-to-use conditions or contrast with other publish tools, so it falls short of a full 5.

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