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

Adds substantial behavior beyond the readOnly/idempotent annotations: default page size of 10, a hard cap of 100, the meaning of `page`, default view=runs, newest-first ordering for versions and notes, and the per-view required identifiers. It also flags that brief prose, notes and excerpts are untrusted data rather than instructions — a genuine prompt-injection caveat no annotation conveys.

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 pagination contract, then walks the views in a compact, semicolon-chained enumeration with no filler. It is a dense single paragraph, so the safety note at the end is easy to skim past, but every sentence carries 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?

For an 11-parameter, zero-coverage, no-output-schema tool this is close to sufficient: view behaviors, defaults, ordering and required identifiers are all present. Missing pieces are the return shape per view and the filterable fields behind `query` and `status`.

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?

With 0% schema coverage across 11 parameters, the description carries the load and does most of it: every view enum value, lens_match=all semantics, company_id/ticker requirement per view, run_id for evidence, and per_page defaults and ceiling. Gaps remain — `query` and `status` are never explained and `lenses` item semantics are unstated.

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 specific verb+resource ("List research") plus its pagination model, then enumerates the five view modes and what each one returns. An agent can tell this is the read/list counterpart to get_research or get_company_research, though it never explicitly contrasts with the overlapping sibling get_company_evidence.

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 selection guidance: use view=runs (the default) for runs with company/individual/joint lens filtering, view=briefs for current briefs, view=versions/notes when you have a company_id or ticker, and view=evidence when you have a run_id. It stops short of naming an alternative sibling tool for cases this one doesn't cover.

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