transaction_metrics

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

With no annotations, the description carries full burden and provides substantial behavior: one logical GET, no auto-fetch of continuation pages, array limits of 100 rows and 256 KiB, truncation reported in text and metadata, and refusal of oversized records without partial fields. This goes well beyond a typical description, though the confusing 'unfiltered capture' sentence and the vague 'required inputs reflect tool policy' line reduce clarity slightly.

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 definition is front-loaded with a useful first sentence, but it is not concise: the second sentence is an ungrammatical test-specific example, and later sentences like 'Required inputs reflect tool policy as well as measured upstream requirements' add little operational value. The useful behavioral notes would be clearer as short bullets.

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 low-complexity, two-parameter GET with no output schema, the description covers request behavior, limits, truncation, and refusal, which is unusually complete on the operational side. It falls short on domain specifics needed to invoke correctly, such as metric name vocabulary, date format, and the meaning of 'other declared filters', so the agent still has meaningful gaps.

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 0%, so the description must compensate; it does add meaning by identifying 'from' as an explicit date and showing that 'metrics' is a comma-separated list of named series via 'battles,battles-modern'. However, it does not specify date format, valid metric names, or whether 'from' is inclusive, and the 'other declared filters' phrase conflicts with additionalProperties=false.

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?

Opens with a clear verb+object+qualifier: 'Read named transaction metric series from an explicit date,' which conveys the operation and distinguishes it from sibling transaction lookup tools. However, it never names a sibling or an exclusion, and the following sentence about 'battles,battles-modern' is a garbled example that muddies the otherwise crisp purpose.

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 first sentence implies this is the tool for reading named metric series at a specific date, and the note about one GET and no continuation pages gives operational context. But there is no explicit when-to-use versus alternatives, no prerequisites, and no 'use X instead' guidance, so the agent must infer the decision boundary from the tool name and siblings.

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