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

Annotations already declare readOnlyHint/idempotentHint/non-destructive. The description adds substantial context beyond that: 'All data is pre-computed by the Stocklake AI pipeline — no live AI calls on request' (latency/cost profile), 'Pro tier only' (access), and nuanced result semantics like signals being 'recency-gated, not gated on whether Stocklake's own trading engine still holds the signal live' and the null fallback for pre-schema summaries. This materially changes how an agent should interpret 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 long, but every sentence carries operational value — cross-tool scale/sync conventions (ai_score vs signal_score), null-fallback logic, gating rules, and disclaimers. It is front-loaded with purpose and replacement info before the return breakdown, and uses clear bulleted sections. Length is justified by the five-domain output and the ambiguity it resolves, though it edges toward the upper limit.

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 one-parameter tool whose output aggregates four distinct source tools with cross-tool consistency guarantees, the description is thorough: it explains the sync semantics of signal_score across news/sentiment/signals, the fallback behavior for pre-schema fields, the recency gating, and the version-shipped nulls. The existence of an output schema offloads return-value shape, so the description's job of explaining semantics is fully met.

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 single 'symbol' parameter is already well-described in the schema ('Stock ticker symbol to fetch the full AI research bundle for'). The description repeats the one-parameter nature but adds no new syntax or format guidance beyond what the schema provides, so it sits at the baseline for high-coverage schemas.

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 first line states a specific verb+resource: 'Full AI research bundle for a stock in one call.' It enumerates the exact data domains (fundamentals, AI summary, news, insider/institutional signal, trade signals) and explicitly names the four sibling tools it replaces (get_stock + get_stock_news + get_insider_activity + get_signals), which provides crisp differentiation against the 16 siblings.

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?

It says exactly when to use this over alternatives: 'Replaces 4 separate calls' — an explicit routing hint. It also flags the Pro-tier access constraint. The one gap is the lack of an explicit 'use the single-domain call if you only need one type of data' exclusion, but the replacement framing makes the trade-off clear enough.

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