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

readOnlyHint=true already covers the safety profile, but the description adds real behavioral context beyond annotations: default ordering (newest first), the return envelope {count, results}, and the ElasticSearch-style filter mechanism. It does not mention pagination limits or rate limiting, but pagination is covered in the 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?

Three tight clauses: what it lists, default ordering plus optional filter, and the return shape. The scoping and filter information is front-loaded and nothing is wasted.

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 takes on the burden of return-value disclosure and does provide {count, results}. For a read-only list tool with fully documented parameters, that is nearly sufficient; only the meaning of 'count' (total matches vs. page size) is left ambiguous.

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 the schema already documents from/size semantics, filter syntax with examples, sort_field and sort_direction defaults. The description adds only a generic reference to ElasticSearch-style querying, which the schema demonstrates more concretely. Baseline 3 is appropriate.

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 (list/search) and resource (contacts), then enumerates the record subtypes it covers (customers, leads, adjusters, subcontractors), which distinguishes it from the sibling list_jobs/list_tasks/list_invoices. It even names the underlying endpoint, so the agent knows exactly which collection is being read.

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 description conveys that filtering is optional and that results come newest-first by default, which implies 'use this for browsing/querying contacts.' However, it never states when to prefer this over jobnimbus_get_contact for a single lookup, nor any conditions under which filtering is required or unsupported.

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