Lodging Decision

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses determinism ('deterministic given identical input'), non-persistence ('does not persist any data'), non-transactionality ('does not book or transact'), and privacy behavior ('does not infer or profile demographics'). This is comprehensive for a decision tool, though it does not mention rate limits or error handling.

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?

The description is front-loaded with the core action in the first sentence, then covers scope, exclusions, and caveats. It is relatively long but each sentence adds value—no fluff. The structure with 'SCOPE' and separate exclusions makes it easy to parse.

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?

Given the tool's complexity (3 top-level params, nested objects, no output schema), the description provides a clear outline of what is evaluated and what the return contains ('score breakdown, tradeoffs, risk flags, missing information, and confidence'). It adequately describes inputs via the scope and explicit requirement for candidate listings. It could be more detailed about output format, but it is complete enough for an agent to use the tool correctly.

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 schema has 0% description coverage, so the description must compensate. It adds meaning by stating the evaluation scope ('budget, location, amenities, workspace ergonomics, acoustic isolation, price sanity vs submarket baselines, keyless access friction, and Safety & Belonging') which maps to several parameters, and explicitly requires candidate_listings. However, it does not explain the purpose or format of individual parameters beyond this scope, leaving some inference needed for max_guests, nightly_rate, etc.

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 description states exactly what the tool does: 'Ranks caller-supplied lodging candidates for a traveler/trip and returns a deterministic, evidence-backed recommendation with score breakdown, tradeoffs, risk flags, missing information, and confidence.' It also clarifies what it does NOT do (search inventory, book, transact, persist data), making the purpose unambiguous and distinguishing it from any potential alternative.

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?

The description explicitly states that the caller must supply candidate_listings and that the tool does not book or transact, setting clear expectations. It also advises to 'Always re-verify availability, price, and policy before booking,' implying the tool's output is static and not a live booking action. While there are no sibling tools to compare against, the context of when to use this tool is clear.

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