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

With no annotations, the description carries the behavioral burden and does disclose key traits: sandbox-only, no live provider call, no real payment, and the synthetic/bounded nature of the snapshot. It does not mention auth, rate limits, or error behavior, but those are less critical for a read-only sandbox snapshot.

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 reasonably compact and front-loads the resource, but the opening sentence largely repeats the tool name and the final sentence repeats the required-field list from the previous sentence. The vague 'capability id field(s)' also adds ambiguity without adding clarity.

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 tool with a generic schema and no annotations, this description provides important fixture and sandbox context and names the required request fields. However, it does not clarify the discover/invoke split among siblings or explain what 'capability id field(s)' means, so an agent could still be unsure which sibling to use. The output schema covers return semantics, so that gap is acceptable.

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 only exposes an opaque request object with additionalProperties true, so the description must compensate for zero schema coverage. It lists the required nested fields (schema_version, data_mode, fixture_id, item_id) and instructs the caller to pass the full request object, which is essential. It stops short of providing types, formats, or a precise definition of the vague 'capability id field(s)'.

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 clearly identifies the resource ('public offer') and the action ('snapshot') for a single item id, and adds that it is sandbox-only and synthetic. It does not explicitly contrast with the discover_* sibling for the same public-offer resource, so differentiation relies mostly on the tool name.

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 states this is sandbox-only, makes no live provider call, and involves no real payment, which gives clear context for when this tool is appropriate. It does not explicitly name alternatives or exclusion conditions, but the sandbox/synthetic framing is strong enough to guide selection.

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