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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that with the return field list (340B ID, entity type, state, participating status, contract-pharmacy count) and the dataset scale (~93k entities), which tells the agent what a hit looks like and how selective a name query must be. It still omits pagination/truncation behavior for large result sets.

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?

Two short sentences with zero filler: the first states the resource, its subtypes, and the query key; the second states what comes back. Nothing repeats the schema or pads the definition.

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?

With no output schema, the description steps in by enumerating returned fields and the corpus size, which is enough for an agent to plan a call. It is slightly short on what happens when a search is too broad (pagination/truncation) and on how this differs from pharmacy_340b_clients, so it is not fully complete for a search tool in a crowded sibling set.

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%: q (name, >=2 chars) and limit (default 25, max 100) are both fully documented in the schema. The description only echoes the name-search intent and adds nothing about minimum length, defaults, or caps, so this sits at the baseline for a fully documented schema.

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?

Specific verb (Search) plus a precisely defined resource (HRSA 340B covered entities) with the entity subtypes spelled out in parentheses (disproportionate-share hospitals, FQHCs, clinics). It also states the searchable key (name) and the full return field set, so the agent can distinguish it from generic tools like 'search' without opening the schema.

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?

The phrase 'by name' implicitly scopes usage to name lookups, but there is no explicit when-to-use/when-not guidance and no reference to adjacent tools such as pharmacy_340b_clients or the generic 'search'. An agent can infer the use case but is given no routing help among the many sibling search tools.

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