eds_info

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

With no annotations, the description carries the full behavioral burden, and it does add real value: signals are stored at pricing time, outcomes are recomputed from the same internal APIs, and a running hit rate is published at a free track-record endpoint. However, it never completes the sentence describing what the tool actually returns, and it does not clarify whether this is a free informational lookup or a priced purchase despite the "[FREE]" and "priced recommendation" phrasing creating tension.

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 content is dense and information-rich but delivered as a run-on sentence chain, and the ending is cut off mid-word, which is the definition of not being front-loaded cleanly. The topic/horizon enumeration is justified; the source-list parenthetical is borderline but defensible as it grounds the verifiability claim.

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 tool with no annotations, no output schema, and no parameters, the description must explain both what comes back and how to drive it — and it does neither, terminating with "This tool returns s". An agent reading this knows the product concept but cannot predict the response shape or the mechanics of obtaining a signal.

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?

The schema has zero parameters, which normally sets a baseline of 4, but the description introduces topics and horizons that read like selectable inputs while the schema exposes no way to specify them. That mismatch creates ambiguity rather than clarity about how the caller steers the tool, pulling the score below the parameterless baseline.

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 names a specific product ("EDS - Economy Decision Signal") and states concretely what it produces: a priced recommendation with a verifiable outcome recomputed from named internal sources (AgentWorld economy, x402 settlement pulse, AGWC Uniswap V2 pool, SolvScore). It also enumerates the topic domains and their outcome vocabularies, which is unusually specific. It stops short of a 5 because the final sentence is truncated ("This tool returns s") and it never contrasts itself with the near-namesake sibling solvscore_decision_info.

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?

There is no statement of when an agent should call this tool versus alternatives such as solvscore_decision_info, data_economy, get_settlement_pulse, or get_economy, all of which overlap in subject matter. The topics and horizons are listed as if the agent could choose among them, but with zero parameters there is no guidance on how that selection happens or what the caller should do next.

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