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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety profile is covered. The description adds useful context beyond annotations: tier-based limits (FREE returns up to 3 holdings), the possibility that values may be absent when no completed score exists, and that it targets the user's watchlist specifically. This is meaningful behavioral disclosure that complements the annotation set.

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?

Three sentences, zero waste. Front-loads the primary purpose, covers edge cases (absent values), notes tier limits, and ends with a clear usage recommendation. Every sentence earns its place.

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?

An output schema exists but has no nested objects, so the description reasonably handles the complexity of tier-dependent data. It covers the key variability (plan limits, absent scores) that a schema alone wouldn't convey. Could arguably note that without a completed score no data is returned for that stock, but it already says 'either value may be absent' which sufficiently telegraphs the behavior.

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?

Zero parameters exist, so the schema cannot carry any burden. The description compensates by explaining what is semantically returned (composite scores and grades, absent values, tier-dependent holdings count). With 0 params, baseline is 4, and the description earns it by clarifying the return semantics that vary by tier.

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?

Specific verb+resource ('Retrieve StockLens analysis summaries') with clear scope ('for the authenticated user's watchlist'). Explicitly states what it returns (composite scores and grades) and the tier-dependent behavior (FREE=3, PRO/MAX=full). Clearly distinguishes from siblings like initiate_analysis and fetch_analysis_result which do different jobs.

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?

States when to use it: 'Use this to give users an overview of their portfolio's analytical health.' It implies alternative tools exist for deeper operations (initiate_analysis, fetch_analysis_result), though it doesn't explicitly state when NOT to use this or name alternatives directly. Decent contextual guidance for how this fits among siblings.

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