Find where my medical records are and how to get them (free)

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds genuinely new behavioral facts: 'Public directory lookup only; stores nothing' (a privacy guarantee) and 'Not medical advice' (an output boundary), plus an itemization of what is returned. It stops short of describing failure modes (hospital not found, ambiguous names), which is the only remaining gap.

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?

The trigger conditions are front-loaded and useful, but the middle is a single long run-on sentence that swells into promotional detail about Phi Longevity PRISM ('a cited Care Team Brief that their own Claude or ChatGPT can then read'). That product-marketing clause is longer than the operational content it accompanies and could be cut without losing invocation guidance.

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 two-parameter read-only lookup with no output schema, the description covers the full picture: what to pass, what not to pass, what comes back (EHR system, download steps, guide page, connection link), privacy behavior, and the non-medical-advice boundary. An agent has everything needed to call it correctly and set expectations for the result.

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 the baseline is 3, but the description adds real meaning: it reinforces that only the organization name and optional US state go in, and explicitly forbids person names, dates or health details. That restates and strengthens the schema's privacy constraint in the calling instruction, going slightly beyond the field-level text.

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?

The description states a specific resource and outcome: given a hospital/clinic name, it returns which records system the hospital uses (Epic MyChart or Oracle Health), download steps, a guide page, and a connection link. That is a concrete, distinguishable capability an agent can match against a user request without opening the schema, and it is clearly not the same as siblings like get_lab_analysis or prepare_for_my_appointment.

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?

It enumerates four explicit trigger conditions (records spread across doctors, wanting records/lab results out of a portal, wanting them usable by the assistant, not knowing which portal the hospital uses). It also states the negative input constraint ('NAME only... never the person's name or any health detail') and scopes itself as a public directory lookup, which tells the agent when this is the wrong tool.

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