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

With no annotations, the description carries the full behavioral burden and does reasonably well: it discloses the return shape (data.events plus top-level page), that empty events means no matches, and the exact pagination contract. It omits auth/rate-limit behavior beyond what the schema already says about market-restricted keys.

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-loads the one-line summary then adds three tightly scoped sentences about the return shape and pagination. Little waste, though the indented multi-line layout is slightly noisier than plain text.

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 6-optional-parameter, no-output-schema tool, the description compensates by explaining the returned fields and pagination flow, which an agent needs to chain calls correctly. Introducing the return contract in prose covers the absent output schema adequately.

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 100%, so the schema already documents defaults, ranges (1–500), formats (YYYY-MM-DD), and symbol limits. The prose adds only the cursor verbatim rule, which is marginal on top of the structured fields, so the baseline 3 applies.

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 and resource ('Get dividend events') plus its filtering and pagination scope, so the agent knows what it returns. The word 'calendar' implies a date-oriented listing, which separates it from get_dividends/get_dividends_ttm, but the description never explicitly names or contrasts those 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?

Gives clear operational guidance for the follow-up call: keep filters unchanged, pass page.next_cursor verbatim, reuse data.from/data.to if dates were omitted. What is missing is when to choose this tool over the sibling dividend endpoints (get_dividends, get_dividends_ttm).

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