Start a lab-results analysis and collect it later (made-up or de-identified numbers)

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

Annotations already mark this read-only, open-world and non-destructive, but the description adds genuinely new behavior: the async job pattern, an expected 30-60 second runtime, a 30-minute result retention window, and the fact that no clinician reviews the output. The PHI constraint ('never names, dates or record numbers') is a critical operational caveat that annotations cannot express.

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?

Front-loads the identity of the analysis and the async/job mechanics before the output inventory, and every clause carries content. The opening sentence is long and the parenthetical output list is dense, but 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?

There is no output schema, so the description must explain return values, and it does: the health picture components (plain-language story, graded connections, doctor questions with urgency, due tests, safety notes, unknowns) plus the recommendations shape and the job_id. Combined with the timing and retention notes, an agent has everything needed to call it and to poll correctly.

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 50%: biomarkers and conditionFocus carry schema descriptions, while age and biologicalSex do not. The description reinforces the biomarker constraint (made-up or de-identified values only), which is valuable, but adds nothing about what age or biologicalSex are used for. Baseline 3 is appropriate given the partial coverage gap.

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 action and resource: it produces a PRISM 2 lab-panel reading (model reasoning plus a second automated check), and returns a job_id rather than the reading itself. It also positions itself against explain_my_lab_results by saying the output has the 'same recommendations shape', implying PRISM 2 is the deeper variant, though it never names a clear contrast with full_prism_report or quick_check.

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 explicit follow-up mechanics: call get_lab_analysis with the job_id after about 30 seconds, pending until ready, result kept 30 minutes. That is precise when-to-use guidance for the retrieval sibling. It stops short of saying when an agent should pick this over quick_check or explain_my_lab_results, leaving that comparison to inference.

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