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

Annotations already cover safety (readOnlyHint, destructiveHint=false, openWorldHint), so the bar is lower, and the description still adds real behavioral substance: the bounded six-preview scope, the returned row shape (dated rows plus per-category purchase/sale, holdings-change, commentary and derivative directions), and the non-obvious rule that awards are non-directional. It omits auth/permission requirements and any latency or freshness caveats, keeping it short of 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?

Front-loaded with the core action and return shape before the disclaimers, which is the right ordering. The closing negation list runs five items long, and 'Awards are non-directional' is terse to the point of opacity, but no sentence is pure padding.

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?

There is no output schema, so the description correctly carries the burden of describing what comes back (original dated rows plus per-category directions). For a single-parameter descriptive read tool, that plus the scope and exclusions is nearly everything an agent needs; only the ticker-format detail is left entirely to the regex.

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 description coverage is 0% and the single property only carries a regex pattern, so the description must supply the meaning. 'For one US stock' usefully constrains the ticker to a US equity symbol, but it adds nothing about format, case, or exchange-suffix behavior already implied by the pattern. Baseline 3 with one param and thin schema documentation.

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?

States a specific verb (inspect) and resource (agreement/conflict across the six bounded AlphaYou smart money previews) scoped to one US stock. It explicitly fences itself off from sibling-adjacent concepts (confluence scanner, distinct-actor count, scored signal), so an agent can distinguish it from get_smart_money and the other AlphaYou tools without opening a schema.

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 scope statement ('for one US stock') and the negative list ('not a market-wide confluence scanner... not a saved alert') make the intended use case clear and rule out plausible misuses. However, it never names an alternative tool (e.g. get_smart_money) or states the condition that should route the agent there, so routing is left to inference.

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