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

The description discloses key behavioral traits beyond the readOnlyHint annotation: real-time vs 24-hour delay depending on Pro key, thesis stripped without key, identical impersonal feed for all subscribers, and that filters never change signal content. This adds valuable context about data freshness and customization limitations.

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 8 sentences and includes redundant phrases like 'identical, impersonal' and repeats 'impersonal' in the disclaimer. While it covers important caveats, it could be tightened. The core purpose is front-loaded, but the extra disclaimers and redundancy make it less concise than ideal.

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 there is no output schema, the description compensates by enumerating the fields carried by each alert (feed, tier, side, price, model probability, edge, market link). It also covers Pro vs non-Pro behavior, feed identity, and filter semantics. This is comprehensive for a read-only tool with full schema coverage.

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 the baseline is 3. The description adds meta-semantics by noting that filters (feed, min_tier, since) SELECT alerts without altering signal content, which clarifies the conceptual role of parameters beyond their syntactic definitions. This elevates it to a 4.

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 opens with 'Read the edge alerts our models generate on Kalshi' which specifies the verb (read) and resource (edge alerts). It explicitly lists alert types (weather, bitcoin/silver/gold/oil, mispricings) and gives example use cases, clearly distinguishing it from focused siblings like commodity_edge or nfl_edge.

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 provides explicit use-case phrases: 'Use for "any edge on Kalshi", "weather trade signals", "latest mispricings".' It also explains that filters select alerts without changing content, which helps the agent understand how to tailor queries. However, it doesn't explicitly name alternative tools for specific subdomains, leaving some ambiguity.

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