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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: an Authorization Bearer session is required, the event window is capped at 20 per canary, and returned labels are untrusted text delivered in an untrusted envelope — a security-relevant disclosure.

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?

Two sentences, front-loaded with the return payload before the auth and trust notes. The long parenthetical field lists are dense but each item is substantive rather than filler, so it stays close to earning every word.

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?

With no output schema, the description carries the full burden of explaining return values, and it does: reading fields (nonce, code, balance, checks) and event fields (trigger, severity, evidence, test flag, plain-language reading, recommended action) are all named, plus auth and trust handling. Nothing needed to call it 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 there is nothing for the description to disambiguate; baseline 4 applies. The schema is trivially complete.

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?

Names a specific resource (every canary you registered) and enumerates exactly what is returned: the watcher's last reading plus the newest 20 events per canary. The pairing with canary_register is implied by 'every canary you registered', but the sibling is never named, so an agent gets no explicit routing cue.

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?

Usage is only implied: this is the read side of the canary lifecycle. There is no explicit statement of when to call it versus e.g. since_last or detections, and no exclusions or prerequisites beyond the auth requirement.

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