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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: data comes from a 'self-hosted official snapshot', results are bounded/paginated, and each response carries coverage, a raw-package hash and attribution. It stops short of stating rate limits or what happens on an unknown series.

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?

Three sentences, front-loaded with the core verb/resource, then the returned contents, then usage examples and scope. Mild redundancy between 'bounded history' and the 'pagination' item in the contents list, but nothing is wasted.

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 responsibly enumerates what comes back (series metadata, values, pagination, D1 coverage, raw-package hash, attribution) and bounds the temporal scope. The one gap for a 6-parameter tool is that it doesn't explain how to obtain a valid series identifier if the exact H.15 name is unknown.

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 every parameter including the series alias formats and date patterns is already documented in the schema, making 3 the baseline. The description only reinforces the bounding concept via 'bounded history' and does not add syntax or resolution behavior beyond the schema.

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 ('Return a bounded history for one ... H.15 business-day rate series') plus scope ('2000-present', 'not a live market quote'), which is enough to distinguish it from fed_board_h15_yield_curve and fed_board_h15_rate_spread. It never names those siblings explicitly, so the differentiation is by inference rather than declaration.

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?

Three example queries ('show the effective federal funds rate history', 'get daily 10-year Treasury yields', 'what was prime over this period?') imply when the tool fits, and the '2000-present ... not a live market quote' line excludes real-time use. However, it never points to fed_board_h15_search_series for discovering valid series identifiers, nor explains when the evidence_pack or yield_curve siblings are preferable.

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