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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new context the annotations lack: the 14,000+ corpus size and an enumeration of returned fields including HUD 232 loan match status (active, past, none) and the SNF Register page. It omits paging behavior and what happens with zero filters, keeping it below a 5.

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 sentences, both front-loaded with the operation and then the handoff. The middle clause is a long comma-separated return-field list that reads as a run-on, but every element is substantive rather than 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?

With no output schema, the description carries the return contract itself and does so field by field, which is exactly what an agent needs. Combined with the 100%-covered input schema and annotations, nothing blocking a correct invocation is missing, aside from minor filter-combination nuance.

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 all eight parameters are self-documenting with examples, enums and defaults, making 3 the baseline. The description only echoes the name/city/state match axes and does not mention that min_stars or hud_loan act as filters (it presents loan status only as a result field), so it adds little beyond the 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?

Names a specific verb and resource ('Searches the 14,000+ CMS-certified nursing homes') and pins down the three matching axes (name, city, state) plus the exact fields returned. It also routes the agent to get_nursing_home for detail lookup, so the boundary with that sibling is visible without opening a 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 final sentence 'Use the CCN with get_nursing_home' gives explicit downstream usage for the primary key returned. It does not, however, distinguish this search from get_state_nursing_homes or rank_states_nursing_homes, so the agent must infer when a broad listing or state ranking is preferable.

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