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

Annotations already declare this read-only, idempotent, and closed-world, so the safety profile is covered. The description adds real value beyond that: paging contract (max 50 per call, loop on meta.has_more with offset=meta.next_offset), the meaning of meta.total for the filtered set, and the fact that from/to apply only to filings. Return-field semantics for meta are disclosed even though no output schema 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?

Front-loaded purpose followed by a scannable per-type bullet list and a single paging sentence; nothing is padded. Slightly dense at the end where paging, date bounds, and meta.total are packed into one sentence, but every clause carries operational information.

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?

With no output schema, the description does the work of describing return shape (meta.has_more, next_offset, total) and per-type row fields, and it documents the pagination loop an agent must implement. Remaining gaps are modest: no note on auth/rate limits, and no resolution of the required-symbol ambiguity across the three alias parameters.

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 every parameter and the baseline applies. The description contributes one genuinely cross-cutting clarification — that from/to constrain filings only — which is a conditional relationship not obvious from per-parameter text. It does not explain the symbol/ticker/identifier alias interplay or reconcile the statement that symbol is REQUIRED with the empty required list, both of which would matter at call time.

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 concrete verb and resource ('Get stock events') and enumerates the three subtypes with what each returns (sentiment tags for news, ex-date/LTP for corporate actions, doc_type/quarter for filings). An agent knows exactly what data comes back. The one gap is sibling differentiation: get_stock_news, get_corporate_actions, and list_company_documents overlap heavily and none are mentioned.

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 type enum plus per-type payload descriptions imply when each mode applies, and 'from/to (filings only)' scopes date filtering correctly. But there is no explicit statement of when to choose this over get_stock_news or get_corporate_actions, which are the most obvious competing calls in this server. Usage is inferable rather than stated.

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