Cost Check

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely useful behavioral semantics beyond them: the cost model is 'pessimistic,' costs are charged at BOTH entry and exit, and 'always against the position' (i.e. never credited in the trader's favor). That materially changes how an agent should interpret the result.

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 tight sentences, front-loaded with the core transformation before the mechanics. No filler; the closing gym reference is a slight flourish but reinforces model consistency. Slightly jargon-dense but appropriately sized for the task.

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 4-parameter, read-only math tool with an output schema and full annotation coverage, the description supplies what's needed: purpose, cost model, and application semantics. Return values need not be explained since an output schema exists. Only explicit sibling routing is absent.

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 each bps parameter is already documented. The description still adds value by explaining how the parameters combine and are applied twice (spread + slippage + adverse selection charged at entry and exit), which goes beyond the flat per-parameter definitions in 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?

The description states a specific verb+resource: 'Convert a claimed gross edge into net-of-cost reality.' An agent can immediately tell this is an edge-cost computation rather than a validation/planning/sizing tool like its siblings. It stops short of explicitly naming any alternative (e.g. explain_sizing), so it isn't a 5.

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?

Usage is only implied: the word 'claimed' suggests it is for stress-testing a user-supplied edge, and 'the same model the gym scores every episode with' hints at consistency with scoring. There is no explicit when-to-use, when-not-to-use, or named alternative among the sibling tools.

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