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

Annotations only declare safety traits (readOnly, idempotent, closed-world); the description adds the decisive behavioral fact beyond them - on the free endpoint this call returns the coded error UPGRADE_REQUIRED with token instructions - which prevents an agent from mistaking a failure for a real 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?

Four short sentences, front-loaded with the access tier constraint, then purpose, then the behavioral consequence, then fallbacks. Every sentence earns its place and nothing is padded.

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?

An output schema exists so return values needn't be explained, and the description covers access tier, error behavior, and fallbacks. The one gap is the unexplained discrepancy between the described strategy inputs and the empty argument schema.

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 zero parameters the baseline is 4, but the description references inputs (a catalogue slug or an inline rule set) that do not appear anywhere in the empty properties object, creating ambiguity about whether arguments exist rather than clarifying any.

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?

States a specific verb and resource - stress a strategy (catalogue slug or inline rule set) on any ticker - and immediately distinguishes its scope from the cached single-regime tools, so an agent can tell it apart from run_stress_test without opening a schema.

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?

Explicitly gives the when-to-use condition ('use when you want to stress a strategy ... on any ticker') and names two concrete alternatives with their exact scope (challenge_strategy with buy_and_hold/rsi_30_70, run_stress_test with buy-and-hold on one cached regime). Nothing 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.