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

Annotations already declare read-only, idempotent, closed-world behavior. The description adds valuable context beyond that: the no-look-ahead guarantee, the presence of fetched_at and origin (bf:* = backfilled) in rows, and the default TSV output. This gives the agent a clear picture of the data's provenance and safety.

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 dense paragraph that front-loads the core purpose and then efficiently packs parameter guidance. It is appropriately sized for a 15-parameter tool, though the heavy use of shorthand and parentheticals makes it slightly harder to parse on first read.

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 complex tool with 15 parameters and no output schema, the description covers the essential behavioral context: the three kinds, date-range constraints, run selection logic, and output format defaults. It does not explain all returned columns, but given the schema's completeness and the annotations, this is largely sufficient.

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?

With 100% schema description coverage, the schema already documents each parameter. The description still adds meaningful semantics: the from/to constraint (<= 366 days, 1 unit per 31 days), the run/lead/cycle/asof relationships, and the meaning of kind values. It does not repeat the schema verbatim but enhances understanding.

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 it returns 'as-issued history for backtests (no look-ahead)' and enumerates three distinct kinds (daily, nbm, obs) with their respective data. It does not explicitly differentiate itself from siblings like 'forecast', but the 'as-issued/no look-ahead' framing makes its specific niche apparent.

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 context 'for backtests' implies when to use it, and the description explains the semantics of the kind and date parameters. However, it does not explicitly say when to choose this over alternatives such as 'forecast' or 'fetch', nor does it state any exclusions or prerequisites.

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