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

Annotations already establish readOnly/non-destructive, and the description adds real beyond-schema context: the analysis is STORED (cached), activeRun signals a live analysis in progress requiring the caller to wait, and participantUrl only exists when the study is open and minted. These are non-obvious state conditions an agent must respect.

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 the resource contents, and every clause is informative, but it crams several distinct ideas into one run-on sentence with nested parentheticals, making the activeRun and participantUrl conditions harder to scan than they need to be.

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 carries the return-shape burden and does it well, naming the fields, the analysis state signal, and the share-link conditional. The one gap is that it never clarifies the tool's relationship to the sibling read/report tools.

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 50% and the description says nothing about either parameter — it describes return fields instead. studyId is self-evident and workspace is documented in the schema, so the burden is lightly handled, but no added meaning is provided for the parameters themselves.

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?

The description enumerates exactly what 'get one study' returns (questions, response count, open/closed state, stored analysis), and the 'STORED analysis' phrasing implicitly separates it from prism_studies_analyze, which runs analysis. It never names a sibling for explicit contrast, so differentiation is inferential rather than stated.

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?

It gives genuine conditional guidance ('insights.activeRun set = wait for it before citing', 'cite theme strengths when reporting results'), but only about post-retrieval behavior. It never tells the agent when to call this versus prism_studies_list, prism_studies_results, or prism_studies_report.

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