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

Annotations are all false. The description adds valuable behavioral context: the permission model based on fuse burning, the constraint that extension cannot exceed parent expiry, and the default extension period. It does not disclose idempotency or exact error handling, but overall improves understanding.

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 three paragraphs with a clear front-loaded purpose, followed by a constraint, caller list, and use cases. Every sentence is necessary, no fluff. Highly efficient.

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?

Given the complexity of the tool (permission model, parental expiry constraint), the description covers most key aspects. It lacks explicit behavior when requested years exceed parent expiry (error vs. truncation) and does not mention output. Still, provides sufficient context for most use cases.

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 baseline is 3. The description adds meaning beyond schema by explaining the permission implications for the name parameter (who can call based on ownership and fuses). For the years parameter, it repeats schema info.

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 clearly states the tool extends ENS subname expiry, a specific action on a particular resource (subname in NameWrapper). It distinguishes from sibling tools like renew_ens_name by focusing on subnames and mentioning the fuse system.

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 explicitly lists who can call (parent owner always, subname owner with fuse) and provides use cases. However, it does not mention when not to use or directly compare to alternative tools (e.g., manage_fuses for fuses), leaving some room for ambiguity.

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