See a sample lab-results report (free, instant, made-up patient)

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, and the description adds genuine value beyond them: no input is analyzed, the patient is fictitious, and PHI must not be submitted. The retention sentence is the weak spot — it describes a claim link holding 'the submitted values' for up to 30 minutes even though the tool accepts no inputs, which reads as carry-over text and muddies the data-handling story.

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-loaded with the payoff ('Free and instant: returns a complete sample...') and scannable, but it runs long for a zero-parameter demo tool. The non-real-patient point is made twice (in the opening and again as 'not a real patient'), and the retention clause about 'submitted values' consumes a sentence that does not apply here.

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?

Complete on the axes that matter: purpose, safety posture, PHI restriction, and sibling routing, with return values covered by the output schema so no format description is required. The one gap is the retention/claim-link sentence, which is unexplained and inert for a tool with no inputs, leaving an agent unsure whether any data-handling consideration applies at all.

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?

Zero parameters, so the baseline is 4, and the description reinforces this by stating outright that the tool takes none — preempting an agent's attempt to pass demographics. No further parameter meaning is needed or possible.

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 concrete deliverable — a complete sample PRISM report for a made-up 58-year-old with type 2 diabetes — and immediately clarifies it is a fixed sample that analyzes no input. The sibling differentiation is explicit: explain_my_lab_results is named for the compute-your-own-values case, and the fixed-sample framing separates it from full_prism_report and start_lab_analysis.

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 the positive trigger (show the owner what they would get before they sign up) and routes the alternative case explicitly ('For your own made-up values use explain_my_lab_results'). It also sets exclusions for data type (SYNTHETIC or de-identified only) and forbids PHI, leaving nothing to inference.

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