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

The readOnlyHint annotation is supplemented by useful behavioral context: the tool is a read-oriented historical data tool, and it explicitly avoids forward ex-dates. The description also clarifies what data is included (each raise/cut, buybacks authorized versus spent, splits, name changes), which sets user expectations beyond the annotation. No contradiction exists.

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 compact and front-loaded: it opens with the core content, then provides concrete user-phrase triggers, then ends with a concise parameter hint. Every sentence adds useful information and there is no filler. The structure makes the tool's purpose scannable in seconds.

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?

Given the output schema exists and the annotations mark this as read-only, the description covers the main scenarios and data scope well. The missing semantics for 'limit' and 'periods' create a minor gap in invocation confidence, and an explicit pointer to a sibling for forward-looking dates would strengthen completeness. Overall, the definition is adequate for correct use in most cases.

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%, so the description carries the burden of explaining parameters. It briefly mentions 'entity' and 'kind = dividends | buybacks | actions,' which clarifies the kind enum but omits the parameter aliases and the meaning of 'limit' and 'periods.' The description adds some value but leaves two of four parameters effectively undocumented.

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 clearly identifies the tool's resource: how a company returns capital, including dividend-rate history, buyback authorizations versus cash spent, splits, and name changes. It distinguishes the tool from siblings by naming specific data elements and explicitly noting that forward ex-dates are not served. This is a specific and actionable definition beyond the tool name.

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 provides explicit trigger questions: 'did X raise its dividend; is X buying back stock; has X cut it,' which makes it easy for an agent to route user intent to this tool. It also gives a clear exclusion ('Forward ex-dates are not served'), though it does not name an alternative sibling like get_calendar for forward-looking queries. The guidance is strong but not fully exhaustive about when not to use this tool.

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