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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorldHint=false, so the description does not need to restate safety. It does add genuinely useful behavior context: the source is public CMS NPI Registry data and results are NOT the WCB authorization list, each result carrying a confirm-before-booking caveat. It says nothing about result caps, pagination, or behavior when no filters are supplied, so it adds value but leaves operational gaps.

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: the first front-loads the resource and filterable dimensions, the second delivers the critical caveat about authorization. No filler, no restatement of the title.

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 six optional parameters, no output schema, and read-only annotations, the definition is nearly sufficient: it tells the agent what it searches, how to filter, and what the results mean. It stops short on the limit parameter's 20-result ceiling and what fields a result contains beyond the authorization caveat.

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 only 33%, so the description carries real weight, and it names the meaningful filter axes: borough or ZIP, specialty, language, and accepting new patients, which maps to five of the six parameters. The limit parameter and its 1-20 cap, plus any result-ordering semantics, are left entirely to 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?

States a specific verb (searches) and resource (The Comp Desk's directory of medical providers in NYC's five boroughs) and names the filter dimensions. It also explicitly contrasts the tool with the Board's authorization list, so the agent knows this is a discovery tool, not an authorization lookup.

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 clear context for when to use it (finding a provider by borough/ZIP, specialty, language, new-patient status) and an explicit downstream rule: confirm the provider is WCB-authorized before booking. It does not point to any alternative tool or describe when not to use it, but no obvious sibling covers this task.

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