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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is met structurally. The description adds genuine signal beyond that: it separates time-series fields from the 'latest book depth' snapshot and clarifies the granularity tiers, which warns the agent that some returns are point-in-time rather than historical. No rate limits or auth notes are given, but for a read-only analytics tool this is minor.

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 return-content list is front-loaded, followed by usage examples, which is a sensible order for an agent deciding whether to call it. The trailing 'Args: entity; window' is redundant with the schema and could be dropped, costing it the top score.

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?

There is no output schema, so the description carries the burden of describing returns, and it does so thoroughly — listing every series and noting which are snapshot vs historical. The only real gap is the absence of any disambiguation from the sibling perps tools, which matters given three near-namesakes in the same family.

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 coverage is 100%, so both parameters (entity, window) are fully documented in the schema, including the enum values and default. The description only restates 'Args: entity; window' plus '1d to 90d', adding essentially nothing beyond the schema — the baseline 3 applies.

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 gives a specific verb and resource — 'One perp market over time' — and enumerates the returned series (price, OI, funding, taker flow, whale net position, book depth, P&L, leverage), so an agent knows exactly what data this yields. It never distinguishes itself from close siblings such as get_perps, get_perps_market, or get_perps_desk, which an agent comparing these four tools would need.

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?

It supplies concrete trigger phrasings ('X funding this week', 'are whales adding to X', 'how deep is X's book') that map real user intents to this tool, which is stronger than generic context. However it names no alternatives and gives no when-not conditions, so the routing against the other three perps tools is left to inference.

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