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

Annotations already declare readOnly/idempotent/non-destructive, so the description adds value beyond them by disclosing data-quality behaviour (returns are measured, 'never padded', sanity-banded) and auth ('no key needed'). It does not cover response shape or how heavily the limit caps output.

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 lead label 'WHAT IS MOVING NOW' is well front-loaded, but the single run-on sentence packs in vague phrasing ('the step to hold the basket with the user's own funds') that adds length without precision. The measured-vs-forecast disclaimer matters, but the delivery clause does not earn its space.

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?

With no output schema and a 4-parameter schema at 25% coverage, the description does convey output content (top-10 ranked list, constituent legs, benchmarks). It still leaves `limit`, `asset_class`, and the 'all' period unexplained, which is a visible gap for a tool whose output can be reshaped by those inputs.

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 only 25%, so the description must compensate; it partially does by enumerating the 1d/5d/10d/30d windows and the SPY/BTC benchmarks, hinting at asset_class. It omits the 'all' period option and gives no explanation of `limit` or the exact asset_class 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?

States a specific resource (top-10 ontology themes) and a specific ranking metric (realised trailing return of a 10-stock equal-weight basket) across named windows. It explicitly excludes the backtested-forecast sibling, but never distinguishes itself from the similarly named theme_journey_top_themes, which is the most confusable neighbour.

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?

'WHAT IS MOVING NOW' implies the screening use case and '(not the backtested forecast list)' names one exclusion, pointing at theme_journey_backtest. However, the closest alternative — theme_journey_top_themes — is never mentioned, so the agent must infer which of the two top-theme tools to call.

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