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

Annotations only establish write/non-destructive/non-idempotent; the description goes well beyond by disclosing consequences (a handoff without a verified chip on a high_value lane raises a finding), the uid_not_in_shipment verify_result distinction, and the terminal-state rule. This is exactly the side-effect detail an agent needs before a write.

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 single dense paragraph, front-loaded with the action and the kind list before the behavioral rules. Every clause carries information, though the verification-result discussion is packed tightly enough to warrant a re-read.

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?

For a no-output-schema write tool with 10 params, the description covers behavior, state transitions, and failure modes well. The remaining gap is that several input fields (location, actor, occurred_at, lat/lng, note) are never explained.

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 description coverage is 0% across 10 parameters. The description adds real meaning for `kind`, `uid`, and `signature`, but says nothing about lat, lng, actor, location, occurred_at, or note, and the verify_result/chip_verify_result terms describe outputs, not params. Partial compensation only.

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 ('Record a custody event on a shipment') and enumerates the exact event kinds, which cleanly separates it from siblings like log_telemetry, verify_chip, and create_shipment. An agent can tell what this tool does without opening the schema.

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 clear when-to-use context for each kind and an explicit exclusion: delivered/cancelled shipments accept only `note` events, and pickup must precede delivered. It does not name sibling tools (verify_chip, log_telemetry) as alternatives, but the state-machine conditions leave little to inference.

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