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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and determinism are covered without the description's help. The description does add one genuinely useful behavioral note: that cross-study participant differences should not be read as a panel trend, which is interpretive context not present in annotations. It says nothing about result volume, ordering, or pagination, so the addition is real but narrow.

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 short sentences, no filler, with the resource scope front-loaded. The density of noun-stacking in sentence one makes it slower to parse than its length suggests, which keeps it off a 5.

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 parameters and no output schema, the description carries the burden of explaining what a call returns, and it only vaguely gestures at 'structured studies' without saying whether the result is a list of IDs, titles, or full records. It also does not disambiguate from get_study. Adequate for a trivial zero-arg list, but the return shape gap matters more here precisely because no output schema exists.

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?

The tool takes zero parameters, so the baseline of 4 applies. There is no schema surface for the description to explain, and it does not waste words restating inputs.

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 verb 'discover' plus the resource 'studies' signals a listing tool, and the sibling set contains get_study, so a singular/plural distinction can be inferred. However, the qualifiers 'structured immigrant reported-vote studies, pre-election intentions and source-reference-only research' are dense and domain-jargon heavy, leaving it unclear what a 'source-reference-only' study actually is. An agent can guess the broad purpose but not the content scope.

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 description never says when to call this versus get_study, get_polls, or get_sources, all of which appear to overlap in subject matter. The second sentence ('Different participants are not a panel trend') is an analytical caveat rather than a routing rule. No prerequisites, no exclusions, no alternative named.

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