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

Annotations already mark readOnly=true, idempotentHint=true, and destructiveHint=false, but the description adds meaningful context beyond these: it explicitly states the tool is read-only and idempotent, and further clarifies it does not fetch live exchange data on demand, place trades, or mutate recorder state. It also mentions the data is 'assembled from persisted recorder evidence,' providing useful behavioral context about data sourcing.

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 compact, well-structured three-sentence block. It front-loads the purpose, then lists return contents and parameters, and ends with behavioral constraints. Every sentence earns its place, and the length is appropriate for a tool with 8 parameters.

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?

Given the tool's complexity (8 parameters, 0 required) and an existing output schema, the description covers the essential aspects: what it returns, what filters are available, and what side effects it avoids. It also notes optional full market inputs/lineage, which informs the agent about output modes. No major gaps are apparent.

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 baseline is 3. The description enumerates parameter groups (product/underlying_ticker, source_date/range, mode, limit, offset) but does not add meaning beyond what the schema already provides. It simply restates them in prose without clarifying when to use one filter over another or additional semantics.

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 retrieves Coinbase INTX perp market-factor history assembled from persisted recorder evidence, with specific details about returned rows (venue-pure, contract identity, ATLAS-shaped factor fields, deltas, quality state, optional inputs/lineage). This distinguishes it from sibling tools like deltasignal_coinbase_perp_factors or deltasignal_coinbase_perp_rankings, which target different resources.

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 provides clear context: it is for historical calculation data from persisted evidence, and it explicitly states it does not fetch live exchange data, place trades, or mutate recorder state, signaling when not to use it. However, it does not name alternative tools or provide explicit when-to-use vs when-not-to-use comparisons beyond the exclusion of live data.

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