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

With no annotations, the description carries the full behavioral burden and does so thoroughly: the returned key type (a2l_reg_*) is shown once, the old key remains valid until first use of the new one, retry-on-lost-response semantics are spelled out, other keys are revoked, and three named error codes (rotation_owner_issues_keys, rotation_too_early, rotation_not_applicable) define the failure modes.

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?

Front-loaded with the usage trigger and organized with a bolded header, with every sentence carrying distinct information (trigger, return, retry, eligibility, errors). It is dense and slightly run-on in the eligibility sentence, but nothing is wasted.

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?

Despite having no output schema, the description explains the return value, the lifecycle of old vs. new keys, retry behavior, and all precondition failure codes. Nothing an agent needs to call this correctly is missing.

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?

The tool takes zero parameters, so the schema is trivially complete and the baseline of 4 applies. The description correctly implies a no-argument call.

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+resource (rotate/renew the registration key) and immediately scopes it to unowned agents in the key's last 7 days. It clearly distinguishes itself from siblings like get_status (which points here) and register_agent (which mints the key).

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?

Explicit 'When to use' block gives the trigger condition (key stops working 30 days after minting; act in the last 7 days) and the exclusion (an owned agent asks its owner instead). It even names the sibling that signals when the time has come.

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