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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is fully covered. The description adds genuine value by enumerating what fields come back and warning that source-only entries contain no invented result table (an anti-fabrication guarantee), but it says nothing about error behavior for missing or invalid studies.

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?

Two tight sentences with the core capability front-loaded and the data caveat second. No filler; the payload enumeration is dense but each item is informative.

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 a one-parameter read with no output schema, the description adequately conveys the return shape and the source-only edge case. It still leaves the id provenance and failure modes unspecified, which matters because no output schema documents the error path.

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% and the description says nothing about study_id — its format, where to obtain it (presumably list_studies), or what happens with unknown/unpublished ids. With a single parameter the semantics are guessable, but the description provides no compensation for the empty schema documentation.

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?

Specific verb+resource: 'Read one published study', followed by the exact payload an agent gets (own dates, group sample sizes, rounded respondent percentages, sampling limitations). It implicitly contrasts with the plural listing sibling (list_studies) by emphasizing 'one', but never names that sibling explicitly.

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 single-record framing implies this is the fetch-by-id counterpart to list_studies, but the description never states when to use this versus listing or searching. The one usage-adjacent cue is the source-only caveat, which is about output rather than invocation choice.

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