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 a genuinely non-obvious behavioral fact — an unfiltered call returns an arbitrary page rather than a meaningful result — which prevents a real failure mode. Remaining gaps (max result cap, paging semantics) are partly handled by the page/limit schema and the presence of an output schema.

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, front-loaded with purpose and followed immediately by the actionable constraint. Nothing is redundant and every clause carries information the agent needs.

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 12-parameter, all-optional search tool with sparse schema coverage, the description covers the core intent and the empty-search pitfall but leaves filter-combination logic, specialty vs. taxonomy selection, and sibling disambiguation unaddressed. The output schema reduces the need to describe return values, which keeps this at a minimum-viable level rather than inadequate.

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 only 33% across 12 parameters, so the description must compensate, and it does so partially by naming the three filter families (name, location, specialty) that map onto name/first_name/last_name/organization, city/state/zip, and specialty/taxonomy/entity_type. It never clarifies the distinction between 'specialty' and 'taxonomy', nor how multiple filters combine, leaving several undocumented parameters unexplained.

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 and resource ('Search U.S. healthcare providers and organizations') plus the filter axes (name, location, specialty) and the upstream data source (CMS NPPES). It does not distinguish this tool from siblings like lookup_npi or providers_near, so the agent must infer that this is the general/free-text search rather than an NPI-exact or proximity 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 a concrete usage constraint and its consequence: 'Provide at least one filter; an empty search returns an arbitrary page.' That is useful when-to-use guidance, but there is no explicit routing to lookup_npi (known NPI) or providers_near (distance-based) despite those siblings being the obvious alternatives.

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