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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the safety profile is known. The description usefully adds the uniqueness rule implying conflicts will fail, but says nothing about required permissions, what a duplicate attempt returns, or whether re-publishing updates an existing listing.

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, front-loaded with the action and target, then the constraint, then the parameter rule. No filler or restated schema text.

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 non-idempotent mutation with five parameters and no output schema, the description covers the core action and uniqueness rule but omits error/conflict behavior and what the call produces. Enough to call it, not enough to call it confidently.

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 100%, so parameters are already documented; the description still adds real value by clarifying that code and link are alternatives (at least one required) even though neither is in the required list. It stops short of explaining how title and description interact with the published card.

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 ('Publish one of the user's referral codes') plus the target surface ('on a brand page'), which is concrete and actionable. It doesn't differentiate itself from close siblings like boost_code or refresh_code, so an agent must infer the boundary.

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?

'One code per brand per user' gives an important usage constraint, and 'Provide a code, a referral link, or both' tells the agent how to satisfy the input. But there is no explicit guidance on when to publish versus boost/refresh an existing code, leaving sibling selection to inference.

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