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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds a valuable drift caveat—the lesson body reflects the state when written and must be checked against the current evidence ledger. This informs the agent about data freshness and potential staleness, which annotations do not convey.

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 sentences, each adding distinct information: the core operation, the invocation trigger, and the drift caveat. The description is dense but not bloated. It could be slightly tighter, but every sentence earns its place and the most critical instruction is front-loaded.

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 read-only load tool with simple parameters, the description covers the key operational aspects: what is loaded, when to use it, and a critical data-quality caveat. It does not describe the exact return structure, but no output schema exists and the description hints at the contained fields ('Why:' and 'How to apply:'), which is sufficient for agent decision-making.

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 75%, with caseStudyId, researchRunId, and mcpIdempotencyKey already described. The description adds meaning to lessonIds by clarifying they are the ids from the turn context's lesson listing, connecting the parameter to the tool's purpose. It does not add syntax details, but the contextual mapping is useful.

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?

Description opens with a specific verb+resource: 'Load the FULL body of prior research lessons by id.' It distinguishes itself from the sibling context listing by noting that the turn context already lists lessons with only name + one-line description, while this tool retrieves the full detail. The 'FULL' capitalization signals scope and differentiates it from any summary retrieval.

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?

Explicitly states when to call: 'call this when you need a lesson's `Why:` and `How to apply:` detail before choosing a branch' and adds a specific trigger condition ('especially before proposing a mechanism family a lesson may already have falsified'). It also contrasts with the context-provided summaries, giving the agent a clear decision rule.

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