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

Annotations only mark it as non-read-only, non-destructive and non-idempotent, but the description adds the crucial patch semantics: "Every field is optional and a missing field keeps the current order" and "Orders stay in force until replaced." It also quantifies a rate limit, which annotations cannot express. It does not say what the call returns or whether any order can be rejected, but the merge/persistence contract is the important 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?

Short, front-loaded, and every sentence carries a rule (merge semantics, persistence, pass, rate limit, prefer act). The clipped style — "Send pass." — is cryptic enough that an agent may need to reread, which costs a little clarity for the brevity gained.

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 complex nested order object with no output schema, the description covers the contract an agent most needs: how fields merge, that orders persist, the pass requirement, the rate cap, and the act alternative. Residual gaps are minor — nothing about what a call returns or how a rejected/ignored field is signalled (the vote field hints the rest still applies, but this is not generalised).

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 100% and the nested properties carry long, self-contained explanations, so the description does not need to re-explain them. The one addition — "The plan, rules, quips and intent fields work here too" — is vaguely worded (does it mean top-level equivalents exist?) and does not help an agent resolve ambiguity. Baseline 3 applies when the schema does the heavy lifting.

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 first sentence gives a concrete verb and resource — "Give orders to your mech and optionally say a line on the radio" — and the description pins where those fields go ("Put the fields inside command"). It differentiates from the closest sibling by naming act and recommending it, though other siblings (take_command, release_command, next_report) are never positioned relative to this tool.

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?

"act sends and waits in one call; prefer act" gives an explicit alternative with a stated reason, and "At most 4 commands a second" sets an operational limit. It never states the converse — when send_command is the right choice over act (presumably fire-and-forget rather than wait for a report) — leaving that inference to the agent.

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