get_lost_items

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

No annotations are provided, so the description carries the full burden. It discloses that the tool is read-only (returns lost items) and specifies the default lookback and data retention behavior. However, it does not mention authentication requirements, rate limits, error handling, or pagination behavior, leaving gaps in transparency.

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 concise, consisting of three short sentences that front-load the main purpose. It avoids unnecessary detail and is well-structured for quick comprehension.

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?

The presence of an output schema reduces the need to describe return values. However, with 0% parameter description coverage and the tool having three siblings, the description could be more complete by explaining pagination parameters and offering comparisons to related tools. As it stands, it is minimally adequate.

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 input schema has three parameters (limit, offset, host) with no descriptions (0% schema coverage). The tool description does not explain what these parameters do or how to use them. This leaves the agent without guidance on parameter semantics, which is a significant gap.

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 states the tool returns auctions where the user bid but did not win, which is a specific verb+resource combination. It also references the underlying API and distinguishes itself by mentioning the same response shape as 'get_watchlist', differentiating it from siblings like 'get_won_items' or 'get_active_bids'.

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 provides context such as the default lookback period of ~30 days and that older items roll off, but it does not explicitly explain when to use this tool versus alternatives like 'get_active_bids' or 'search'. The usage is implied but lacks direct guidance or exclusions.

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