market_history

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

With no annotations present, the description carries the full burden of behavioral disclosure, and it excels. It explicitly discloses multiple non-obvious behaviors: no auto-paging, local limits on array responses (100 rows, 256 KiB), truncation reporting, refusal of oversized records, and the unproven effect of include_sets. This is far beyond a typical description and gives the agent essential operational expectations.

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 a single paragraph of moderate length, but every sentence contributes substantive behavioral information. It front-loads the core purpose. Slight verbosity exists, such as 'The capture had 126 rows and no proven paging selector', which is implementation detail with limited utility to an agent, but overall the structure is functional and not bloated.

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?

Given no output schema and no annotations, the description covers an impressive range of operational details: request behavior, pagination, limits, truncation, and error handling. However, it does not describe the structure of the returned history data (e.g., fields, units), which an agent would need to interpret the output. Still, for a read tool with such caveats, it is largely complete.

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 must compensate for parameter semantics, but it largely fails to do so. It merely notes that include_sets is forwarded with unproven effect and that required inputs reflect policy, without explaining what 'player' should contain (e.g., name vs. ID) or what format include_sets expects. The description adds almost no semantic meaning to the schema properties.

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 states a specific verb ('Read') and a clear resource ('card market history for one player'), which immediately conveys what the tool does. It distinguishes from general market tools by specifying 'one player', but it does not explicitly contrast itself with sibling tools like market_rental_history or market_volume, leaving some differentiation to the agent's inference.

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?

There is no guidance on when to use this tool versus alternatives. It neither states conditions for preferring it nor explains when not to use it. The only contextual hint is 'for one player', but that is more about scope than usage context. No names of sibling tools are given as alternatives.

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