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

With no annotations, the description carries the full burden and does well: it discloses the exact cost ($1.00 per level), both payment rails with destination addresses, the burn address and quote source, and that upgrades happen one level at a time. It omits reversibility, whether the payment tx must be confirmed first, and what happens at the Penthouse cap, which keeps it below a 5.

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?

Dense but front-loaded: purpose and level list come first, then cost and payment mechanics. The two long hex/Solana addresses consume substantial space but are operationally necessary. Minor cost from cramming two payment alternatives into a single trailing clause.

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 an unannotated paid mutation tool with no output schema, the description covers cost, both payment routes, addresses, quote sourcing, and level semantics. The gap is post-call behavior: it does not indicate whether a success result confirms the upgrade or whether the tx must already be mined.

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%, so baseline is 3, but the description adds real meaning the schema lacks: it defines the tx parameter's amount and accepted chains, ties quote specifically to burnTx with a 30-minute validity window, and establishes that the two payment paths are alternatives. This resolves the mutually-exclusive parameter pairing the schema leaves implicit.

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 ('Upgrade any agent's room in APEX Agent City by one level') and enumerates the five levels (Gilded, Gallery, Garden, Club, Penthouse) plus the visual effect, so an agent knows exactly what changes. No sibling offers this operation, and the scope ('any agent's room', not just your own) is explicit.

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 concrete prerequisite path: the burn route requires calling room_menu first to obtain a live quote and passing it as quote alongside burnTx, while the USDC route needs a tx hash. It does not explicitly say when to prefer USDC over burning APEX or point to room_garden, but the sequencing guidance is clear.

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