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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so safety is covered. The description adds real value beyond that: the ordering rule ('cheapest sulfur first'), the meaning of `cheapest`, and an explicit caveat that single-explosive totals overstate cost because damage carries across a mix. That caveat is exactly the kind of correctness-relevant nuance annotations can't express.

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 purpose and compact at three sentences. The middle sentence mixes output-format explanation with a caveat and an external route reference, and the line breaks break mid-clause, making it slightly harder to parse than necessary, but nothing is padding.

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 return-value burden and does so partly — totals for units and sulfur, ordered cheapest-sulfur-first, with a note on `cheapest`. It also discloses the coverage gap (doors/deployables). What's missing is any hint that a mixed-explosive answer differs and where a tool exists for it.

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 coverage is 100% — both `targets` and `explosives` are documented in the schema, including the `staples` default and slug:count format — so the description need not restate them and mostly doesn't. The phrase '`cheapest` is the best single option' adds terminology but is ambiguous about whether it is a parameter, a response field, or an ordering key.

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 computation (explosives needed) against a specific resource (set of building pieces), and immediately describes what the result contains. It does not, however, distinguish itself from the sibling `get_raid_costs`, which an agent would plausibly consider the same task — the only alternative it names is an HTTP route, not a 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?

Implicit usage is clear (give it pieces, get explosive totals), and it does state a scope exclusion — doors and deployables aren't covered. The one routing hint, 'use /calculators/raid's damage_per_unit', names an HTTP path rather than a callable sibling, so an agent cannot act on it directly from the tool list.

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