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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so safety is covered. The description adds genuinely useful context beyond that: it clarifies that despite being a POST endpoint it is a pure read ('changes nothing'), and it documents paging plus totalCount/totalCountRelation semantics, which annotations cannot express.

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 sentences, zero filler. Search scope and filter semantics are front-loaded, and the read-only reassurance about the POST verb is placed last where it resolves the only surprising detail.

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 13-parameter but all-optional search tool with no output schema, the description covers the essentials an agent needs: filter combination rules, tag matching modes, paging, and the count semantics. It does not describe the shape of returned contact records, but with no output schema that gap is minor given the sibling get_contact tool.

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 100%, so field-level meaning is already documented. The description still adds cross-parameter semantics the schema cannot convey: filters combine with AND, values inside one filter match ANY, tags support all/none, and totalCountRelation distinguishes eq (exact) from gte (lower bound). That is real added value above the baseline 3.

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 ('Find contacts by free text and/or filters') and enumerates the filterable fields, so the agent knows this is a filtered search rather than a plain enumeration. It does not explicitly name the sibling it differs from (e.g. sprucehealth_list_contacts or sprucehealth_get_contact), so sibling differentiation is left to inference.

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 explains how filters behave (AND across filters, ANY within a filter) and that results are paged, which implies the tool's role. However, it never states when to prefer this over sprucehealth_list_contacts or when a direct get_contact lookup is the better path, and no prerequisites or exclusions are given.

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