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

Annotations already flag destructive=true and idempotent=false, yet the description still adds real substance: exactly what is suspended, what is deliberately untouched, that one forensic audit row (security.kill_switch) records each token and its previous expiry, and that all site admins are alerted. The mention of 'previous expiry' signals the suspension is recoverable rather than a permanent revoke, which is precisely the kind of context annotations 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?

Front-loaded with the effect, then scope exclusions, then side effects, then auth, then idempotency, then the mirrored endpoint and return shape. Seven compact clauses with no filler; the semicolon-dense style is heavy but every clause carries operational information.

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?

No output schema exists, and the description compensates by enumerating the return keys ({at, windowHours, suspended, aiWasPaused, auditId, effect}) plus the underlying API route. For a zero-parameter but maximally destructive platform-wide action, an agent has everything needed to decide and to interpret the result.

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 no parameters, so the schema baseline is 4. The description still explains the only implicit input — the KILL_SWITCH_WINDOW_HOURS window defaulting to 24 — which tells the agent the blast radius is configurable but not via this 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 and resource — 'press the platform kill switch: pause every model call and suspend every personal access token' — with explicit scope ('platform-wide', last N hours). The effect is unmistakable and cannot be confused with token-level siblings like merjax_revoke_token or merjax_suspend-adjacent tools.

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?

Gives a hard prerequisite ('Site admins with an admin-scoped token only'), a scope exclusion ('Git, CI, merges and deploys are unaffected'), and a repeat-call warning ('Not idempotent: a second press suspends whatever the window holds then'). It does not explicitly point to the obvious counterpart merjax_undo_kill_switch or contrast with narrower revocation tools, so an agent must infer the escalation path.

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