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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavior the annotations cannot convey: a two-phase sensitive-data gate where currentValue is withheld on the first call, the exact shape of the returned sensitiveGate object, and the instruction to obtain user approval before re-calling. It also documents the error taxonomy (source = export|adapter|api_error, level = error|danger|info) and what currentValue represents.

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?

Front-loaded with the one-sentence purpose, and virtually every subsequent clause carries actionable detail (return shape, code-vs-label distinction, gate protocol, ID provenance). It is one very long run-on block that would scan better as bullets, and acknowledge_sensitive is explained twice, but there is little outright waste.

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?

No output schema exists, yet the description enumerates the returned fields, disambiguates raw codes from human labels, and explains the sensitiveGate branch and how to resolve it. For a read-only four-parameter tool with an approval flow, an agent has everything needed to call it correctly, including the second call after user consent.

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 only 25% — only acknowledge_sensitive carries a schema description — so the description must compensate, and it does: it explains where item_id and marketplace_id come from, that project_id is optional but becomes required (with the list_projects remedy) for multi-project customers, and it reinforces acknowledge_sensitive's gate semantics. All four parameters gain meaning beyond the bare integer/boolean types.

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 ("get the detailed report for ONE listing item of a marketplace") and immediately names the question it answers — why this product fails or warns on the channel. The emphasis on ONE plus the pointer to get_marketplace_report for the marketplace-wide case separates it from its closest sibling without opening either schema.

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 an explicit use case ("use this to explain why one marketplace listing failed") and an explicit alternative for the aggregate case. It also routes the agent to the originating tools for each identifier — list_marketplace_items for item_id, list_marketplaces for marketplace_id — and spells out the project_id fallback path via list_projects when project_id_required is returned.

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