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 is covered. The description adds genuinely useful behavior beyond that: results are paged, and still_open is silently shortened at a sentence boundary by default, which is exactly the kind of lossy default an agent must know about or it will quote truncated evidence.

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?

Three short sentences, front-loaded with the resource and scope before the paging and truncation caveats. 'Paged.' is a maximally economical way to convey a behavior that matters, and no sentence is filler.

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 extra weight and does mention the truncated field name and paging model, plus offset/next_offset usage is covered in the schema. Minor gap: the effective limit cap of 50 is stated only in the schema, not in the description, and the frontier vs open-question distinction is not elaborated.

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 80%, so the baseline is 3; the description still adds meaning by explaining the brief flag and naming the resulting still_open_truncated field, which the schema does not surface. The kind enum and limit cap remain schema-only, hence not a 5.

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 resource with scope: 'The Atlas's open questions (evidence gaps with testable hypotheses) and frontier questions', clarifying what an open question actually is. It also differentiates from the sibling get_question by noting that tool holds the full text, so an agent can pick between them without opening either schema.

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 a clear routing rule for full text ('get_question has the full text, or pass brief=false'), which tells the agent when this tool is sufficient versus when to escalate. It does not, however, say when to prefer this over the search_* siblings for discovery, so guidance is strong but not exhaustive.

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