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

Despite readOnlyHint and openWorldHint annotations, the description adds substantial behavioral detail: point fields (value, date, source id, revision, source-time vs read-time dating), a reserved sentinel with data-use URL for five current-only issuer series, and the shared rolling-hour breadth limit. There is no contradiction with annotations.

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?

Every sentence earns its place and the core purpose is front-loaded. The density of domain jargon ('reconstructible recorder source', 'HISTORY_SOURCE_RESERVED', 'current-only issuer series') makes it less immediately scannable than a plainer two-sentence definition, so it is not a 5.

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?

With no output schema, the description compensates by specifying the per-point return fields, the sentinel/list mode behavior, and the shared breadth limit. Combined with 100% schema coverage and the read-only/open-world annotations, an agent has what it needs to invoke and interpret the tool correctly.

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 100%, so the schema already documents all four parameters. The description mostly restates the 'omit source_id' listing mode and 'inclusive date window,' adding only the 'reconstructible recorder source' nuance, which is not enough to lift it past the baseline.

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 opens with a specific verb and resource: 'Returns free normalized observations for one tracked instrument, one reconstructible recorder source and one inclusive date window.' This clearly narrows the tool against siblings like get_rwa_yields or compare_rwa_snapshots, which are about yields or snapshots rather than source history.

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 implies the main use case (historical observations by source) and gives in-tool query variants such as 'Omit source_id to list the instrument's audited sources.' However, it never names sibling tools or states when to prefer get_rwa_yields or compare_rwa_snapshots, so alternatives and exclusions are left to inference.

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