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

With no annotations, the description takes on full responsibility for disclosing behavior. It reveals important quirks: the `date` parameter is silently ignored for non-enterprise tiers, `days` is tier-capped, and the return order is oldest-first with extra metadata fields. It does not explicitly state 'read-only', but the verb 'Fetch' implies it, and the disclosed tier caps act as rate-limit context. Minor omissions (e.g., no explicit side-effect statement) keep it from a 5.

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 organized into four clear paragraphs, front-loaded with purpose and usage. It is information-dense but not bloated; each sentence carries useful context. Minor redundancy with schema details (e.g., tier caps) is acceptable given their importance. Could be slightly tighter, but overall effective.

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?

Since there is no output schema, the description compensates by specifying the return format: 'array of daily market snapshots (oldest first), each with snapshot_date plus all standard MarketSnapshot fields' and additional response metadata. It also covers edge-case behavior (tier caps, date ignored) thoroughly, making the tool's behavior fully understandable for an agent.

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 meaningful nuance beyond the schema: it explains that `date` is only honored at the enterprise tier and otherwise silently ignored, and it reiterates the `days` default and tier caps in a user-facing way. This is valuable, though the description stays silent on `version_info` and `snapshot_type` (both already well-documented in the schema).

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 a specific verb and resource: 'Fetch a historical time series of daily market-level snapshots.' It explicitly distinguishes this from single-ticker data by stating 'overall market sentiment, not a single ticker' and later name-drops the sibling tool get_ticker_history, making the purpose unmistakable.

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?

Provides concrete 'Call this when...' scenarios (trending market mood, charting α-sentiment, computing averages/momentum) and an explicit alternative: 'For a single ticker's history use get_ticker_history instead.' This gives clear guidance on when to use this tool versus its siblings.

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