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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds substantial context beyond that: it reads a ~4-hour-old cache, does not trigger regeneration, returns a specific 'unavailable' status when no cache exists, and warns that content is AI-generated and not authoritative. These are non-obvious behavioral traits that materially affect how an agent should invoke and present the results.

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 four sentences, front-loaded with the core purpose. Every sentence serves a distinct role: what it is, what it returns, how/when it's generated, cache-only behavior, error case, and usage caveat. No filler or redundant restatement of the tool's name.

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 zero-parameter, no-output-schema tool, this description is complete. It documents the return structure, the refresh interval, the cache-miss behavior, and the AI-generation caveat. The agent has everything needed to decide invoke, interpret results, and communicate them to end users.

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 tool has zero parameters and the schema properties are empty (coverage is trivially 100%). The description correctly adds no parameter noise. Given the 0-parameter baseline of 4, this score is appropriate; the description instead clarifies the output shape and cache behavior, which is more valuable here.

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 'Cached equities market sentiment snapshot,' a specific verb+resource+qualifier that immediately distinguishes this from siblings like get_market_movers or get_market_performance. It also enumerates the exact return fields (overallSentiment, atmosphere, keyThemes, tailwinds, headwinds), leaving no ambiguity about its purpose.

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 clearly establishes the context: this is a cache-only endpoint that never triggers regeneration and may return 'unavailable' if no cache exists. This implies it is suitable for quick, non-authoritative sentiment reads. However, it does not explicitly name alternative tools (e.g., get_investor_sentiment or get_market_performance) for cases where real-time or authoritative data is needed, so it stops short of full exclusion guidance.

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