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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context by disclaiming outputs: no inferred winner and no comparable live prices, which tells the agent the result is a static field-by-field comparison rather than a ranked or priced one. It stops short of describing return shape, but the negative guarantees are valuable.

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?

Two sentences, zero filler, with the core action and scope front-loaded and the output limitations immediately after. Every clause earns its place.

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 and rich annotations, the description correctly focuses on what will and won't be returned, which is the main ambiguity for a comparison tool. It is slightly incomplete in not naming which published fields are returned, but it covers enough for correct invocation.

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 0%, so the description carries the burden for the single parameter. It adds the key semantic the schema cannot express: values must be known/valid hotel IDs (not names or free text) and the count is 2–5, matching the min/maxItems constraints. This meaningfully reduces misuse risk even though it does not describe the item format beyond that.

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 (compare) and resource (hotels) plus the scope constraint (2–5 known hotel IDs), which separates it from find_hotels/search that discover IDs. 'Sourced published fields' is vague about which fields, so the resource is clear but the comparison payload isn't fully pinned down. No sibling is named, but the 'known IDs' framing implies the distinction.

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?

'Known hotel IDs' implies the caller must first obtain IDs via find_hotels or search, which is useful implied usage. However, it never states this as a precondition and never names the sibling to use for discovery, nor does it say when comparison is inappropriate. Adequate but leaves routing to inference.

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