get_corporate_actions

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

With no annotations, the description must carry the full behavioral burden, and it does disclose real caveats: 'Partial pagination is explicit', 'Planned and actual amounts remain separate', and that holder changes do not establish complete future reduction plans. However it never states output/truncation signaling mechanics, caching semantics (only the `no_cache` param name hints), or error behavior on out-of-range dates.

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?

Every clause carries information and the payload/scope statement is front-loaded before the parameter rules. The compression is aggressive to the point of occasional ambiguity — 'Partial pagination is explicit' reads more like a note-to-self than an explanation — but there is no filler.

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 an 11-parameter, no-annotation, no-output-schema tool this is a reasonably complete briefing on inputs and data semantics, but gaps remain: `format` values, `no_cache` behavior, ordering of results, and how truncation is communicated to the caller are all unstated.

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% across 11 parameters, so the description is doing all the work — and it largely succeeds: it documents `kind` values, per-kind date field mapping (FREE_DATE/UPDATEDATE/NOTICE_DATE), `days=1..366`, `direction=all/increase/decrease`, `limit=1..5000`, `max_pages=1..50`, `max_seconds=1..30`, and the code-vs-dates interaction. Only `format` and `no_cache` go entirely unexplained.

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?

Opens with a concrete resource enumeration: 'Raw unlock schedules, repurchase progress or disclosed holder changes', which tells an agent exactly what data comes back and that the tool has three sub-modes keyed by `kind`. It never explicitly names itself a corporate-actions tool nor contrasts with neighbors like get_dividend_data, so it falls short of full sibling differentiation.

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 conditional rules: without `code` you must supply bounded start/end (max 366 days), except for unlock which defaults to the next 30 calendar days including today. It also scopes `direction` to holder_changes only. What is missing is explicit guidance on when to prefer this over related financial/dividend tools in the sibling list.

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