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

With no annotations, the description carries the burden and does disclose that this is a self-contained informational lookup returning portal name, vendor, URL, access instructions, mobile apps, and features, plus reverse health-system usage. It also warns about the inherent limitations of portal data (missing historical, cross-system, or older records), which is genuine behavioral context rather than restated structure. It does not address authentication, rate limits, or what happens when the query is ambiguous or matches multiple systems.

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?

Purpose and returned fields are front-loaded, and the intent bullets are scannable. There is some redundancy: portal brand names appear both in the return-value framing and the bullets, and the download-records and share-records bullets describe the same lookup, so the list is longer than strictly needed.

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 one-parameter read-only lookup with no output schema and no annotations, the description covers the essentials: what it takes, what it returns, why it is useful, and where its data falls short. It falls just short of full completeness by not stating whether a query returns one portal or several, or how ambiguous provider names are resolved.

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 description coverage is 100%, so the single query parameter is already fully documented with its own examples. The description adds only light semantics, confirming that the query may be a health system, hospital, provider, or a portal brand like MyChart or FollowMyHealth, which nudges the agent toward accepting brand names but does not add matching or disambiguation rules.

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 opening sentence names a specific verb and resource: lookup of the patient portal used by a health system, hospital, or provider, and enumerates what is returned. It is clearly narrower than siblings like find_emr_options or compare_emr_options, but one usage bullet ('whether their provider uses Epic, Cerner, Allscripts, or another EHR') directly overlaps with get_emr_vendor, and the description never names a sibling to draw the line.

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?

Six explicit user-intent bullets give concrete when-to-use conditions (portal lookup, sign-up help, portal name such as MyChart, EHR vendor question, record download, record sharing). The closing note routes complete-medical-history cases away to an external URL, which is a real exclusion, though no in-catalog sibling alternative is named.

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