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 genuinely non-schema behavior: the exact relevance ranking order, that HQ location is not a service area, that coverage is country-level unless regions are published, and that AND-combination applies across filters. Return-field enumeration overlaps the output schema, which caps it at 4.

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 is front-loaded, and the ranking chain is a single dense but scannable sentence. The two JSON examples earn their place by demonstrating AND-combined filters. Slight density in the results sentence keeps it from a 5.

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 15-parameter search tool with annotations and an output schema, the description covers the hard parts an agent would otherwise get wrong: ranking, coverage level, HQ-vs-service-area, and filter combination. Pagination and sort semantics are left to the schema, which is acceptable but leaves a minor gap.

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 73%, and the description adds real meaning on top: the country/region/hq_country interplay and its effect on ranking, the semantics of worldwide-only providers in relation to include_global, and coverage granularity. It does not explain sort option meanings or limit/offset pagination behavior, so it is not fully compensatory.

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 first sentence states a specific verb and resource (shortlist providers) and immediately scopes it to a job and place. The ranking chain and result-field list make the tool's output shape unmistakable. It does not explicitly name the boundary with siblings like get_provider or compare_providers, so it falls short of a 5.

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?

Two concrete invocation examples (use_case+country, and use_case+country+region+engagement_model) plus the note that filters combine with AND give implied usage. However, there is no explicit guidance on when to prefer this over get_provider or compare_providers, nor any stated exclusions.

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