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

With no annotations, the description carries the behavioral burden. It discloses that the data path is bounded, retained, and potentially incomplete ('when retained', 'not an independently complete Pyth archive'), which is meaningful beyond a generic read. It does not mention pagination quirks or authorization, but the core behavioral caveat is clearly stated.

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?

Two carefully crafted sentences deliver the core purpose, content, and caveat with no filler. The essential 'observed evidence' caveat is placed at the end without bloating the definition.

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 paginated, retention-bounded tool with no output schema, the description names the returned fields and warns about incompleteness. The schema already covers the important constraints like the 26-hour window, cursor freezing, and feed/source enums, so the missing details are mostly not fatal. It is slightly thin on pagination behavior, but adequate.

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 50%, and the description adds no parameter-level guidance. It describes output fields (price, confidence, publish times, EMA, slots) rather than clarifying how to set feed, from, to, limit, cursor, or source. The schema provides some help, but the description does not compensate for the remaining parameter gaps.

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'), a specific resource ('a bounded retained path of Pyth observations captured by Ratchet'), and the key data fields returned. It clearly distinguishes itself from a full archive and from sibling tools like ratchet_pyth_context by emphasizing this is observed evidence, not a complete archive.

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 caveat that this is 'observed evidence, not an independently complete Pyth archive' provides some context but stops short of saying when to use this tool versus ratchet_pyth_context or other siblings. There is no explicit when-to-use, when-not-to-use, or alternative routing.

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