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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavioral context: this is a demo path with no /verify receipt, and it hard-rejects non-sample canonical_ids. That rejection behavior is exactly the kind of runtime trait annotations cannot express. It stops short of describing output structure or what happens to the rejected call.

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?

Three short sentences, front-loaded with what is returned before the demo caveat and the input restriction. Every sentence carries information; the only minor friction is the terse '/verify' reference, which assumes familiarity with a receipt convention.

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 single-parameter read tool with no output schema, it conveys the return content (peers plus subject market metrics) and the key operational constraint on input. The absence of detail on the shape of the peer/metrics payload is the remaining gap, but the definition is sufficient to call it 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?

Schema coverage is already 100% with the single canonical_id documented as hotel_canonical.id uuid, so the baseline is 3. The description still adds real semantic value by constraining valid values to the sample asset's id only, which the schema does not express.

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?

Names the specific resource returned (the sample asset's competitive set: peers plus the subject's market metrics), so an agent knows this is a composite view rather than a plain asset or market lookup. It does not explicitly contrast itself with get_asset or get_market, leaving the sibling boundary to be inferred.

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 implies usage through hard constraints — it only works on the demo sample asset and rejects any other canonical_id — which effectively tells the agent when this tool is applicable. It does not state when to prefer it over get_market or get_asset for the same sample asset, so the alternative-selection guidance is implied rather than explicit.

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