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

No annotations are provided, so the description carries the full burden. It documents that the tool is proprietary and derived from SolEnrich's own query stream, and it discloses the window semantics (acceleration compares three consecutive windows). However, it doesn't explain what the output format looks like, whether results include divergence classification per token, or how 'attention' is measured/aggregated beyond query velocity.

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 compact, front-loaded with the core purpose first, and efficiently packs the divergence classes, data source, and window sizes. It's slightly dense with jargon (early_signal, distribution_risk, fading) but each sentence earns its place. The parentheses definitions help readability.

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 absence of annotations and output schema, the description provides a reasonable ground floor: it defines the core scoring concept, divergence taxonomy, and window behavior. However, for a ranked-momentum tool with nuanced signal classes, the description doesn't clarify what the returned data structure contains (per-token class labels? raw values?) or how an agent should interpret/combine the divergence classes. It's adequate but leaves interpretive gaps.

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%, and the description adds value by explaining the window parameter semantics ('acceleration compares three consecutive windows of this size'). The description also mentions divergences and windows (1h, 6h, 24h) which aligns with the schema. However, no additional meaning is added for the limit parameter beyond its schema description, which is adequate given full schema coverage.

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 the tool ranks tokens by acceleration of agent attention overlaid with price change, with specific divergence classes. It identifies the resource (tokens) and the action (rank by momentum). It doesn't explicitly distinguish from siblings, though the proprietary 'SolEnrich query stream' angle does differentiate its data source from other market tools.

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 explains the divergence classes and the underlying mechanism (agents researching before market moves), which implies when it's useful. However, it doesn't explicitly state when to use this vs sibling tools like token_trend, trending_signals, or consensus_signal, nor does it give exclusion criteria. The proprietary/unique-signal framing gives context but not explicit alternatives.

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