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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description's real contribution is the documented failure mode when insights have not been generated, plus the batching preference. It stops there – no note on ordering, partial-missing refs, or the max-20 ceiling (that one is in the schema). With annotations carrying the safety load, this is adequate but not rich.

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 dense sentences: what it returns, how to call it, when it fails. Value statement leads, failure path last. No filler or repetition of schema detail.

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?

An output schema exists, so return values need not be documented in detail, and the failure/fallback path is covered. The one meaningful omission is what happens if only some refs are invalid – whether the call fails wholesale or returns partial results – which matters for a batch-of-20 tool.

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%, so baseline is 3. The description raises it by explaining the provenance of 'insightRefs' (refs come from get_interview_study) and the intended batching pattern, which the schema's bare 'Insight refs, e.g. ["F1","F3"]' does not convey.

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 (read) and resource (generated insights) and enumerates what comes back: summary, research goals, participants, verbatim quotes. The phrase 'by ref from get_interview_study' plus the ref-based fetch clearly separates it from get_insight (single), list_insights (listing), and the transcript tools.

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 both the positive rule ('Pass every insight you need in one call') and the negative condition with an alternative ('Fails when insights are not generated; use the transcript tools then'). The prerequisite source of refs (get_interview_study) is named explicitly, leaving nothing to infer.

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