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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description goes far beyond them: it discloses that the new key is shown once, that the calling key survives until first use of the new key (so a lost response is recoverable), that other registration keys are revoked, and it names three specific failure codes (rotation_owner_issues_keys, rotation_too_early, rotation_not_applicable) plus grace-renewal constraints (30 days, not in a batch, nothing else callable). This is exactly the behavioral depth that structured fields cannot carry.

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?

A bold 'When to use' header front-loads the eligibility rule, and every sentence carries an error code, timing window, or recovery rule. It is dense and slightly repetitive (ownership restriction is restated twice), but nothing is filler and it remains scannable.

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?

There is no output schema, and the description fully compensates by describing the returned key, its one-time display, and persistence semantics. For a zero-param mutation tool with an unusually complex eligibility contract, nothing an agent needs to call it correctly is absent.

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 there is nothing for the description to disambiguate; the baseline for 0 params applies. No parameter syntax is missing.

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 specific verb+resource ('rotate_key' / 'Returns a new registration key (a2l_reg_*), shown once') and distinguishes the operation from lookalikes: 'This renews a key you hold; it does not recover a lost one.' It is unmistakably distinct from siblings like get_status or verify_credential.

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 ('in the key's last 7 days'), when-not ('Only for an agent nobody owns... an owned agent asks its owner instead'), and routing pointers to get_status (api_key.rotate_from) and next_call. It also names the alternative path (owner issues keys) so the agent never infers eligibility.

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