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

Annotations already declare readOnly=true, destructive=false, openWorld=false, so the safety profile is covered. The description adds real behavioral context beyond that: sort order (newest first) and the full set of returned fields. It stops short of disclosing pagination or result-size limits, which for a workspace-wide list would be the remaining useful detail.

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 with scope, then return fields, then routing to siblings — a logical ordering with no filler. The em-dash enumeration is dense but each item (origin types, sort order, returned fields) carries information; the only slight cost is that the field list makes the first sentence long.

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 compensates by enumerating the returned fields, and with only one fully documented parameter the schema burden is low. What remains unaddressed is list mechanics — pagination, caps, or how large a workspace list can get — which is a minor but real gap for a listing endpoint.

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 coverage is 100% and the single workspace parameter is described thoroughly in the schema itself (token-type behavior, override semantics, API-key exemption). The description adds nothing about the parameter, 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 (list) plus resource (studies) and explicitly enumerates the scope it covers — standalone, canvas-node, and series waves — which is precisely the boundary that separates it from the per-node sibling. It also names the returned attributes (title, question count, response count, state, parent field/node/series), so an agent knows exactly what it gets.

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?

Frames the tool around a concrete question ('which studies do we have?') and contrasts it with two named alternatives: prism_studies_list for the per-node view and prism_research_digest for the findings view, plus prism_studies_get for retrieval of a single study. Routing is explicit with no inference required.

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