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

Annotations only declare readOnlyHint=true; the description adds real behavioral context: filters combine with AND, results are paged via offset/limit, and next_offset indicates where to continue. That paging contract is the key non-obvious behavior. It stops short of describing what the response objects contain beyond the id.

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?

Five short sentences, front-loaded with the core purpose, then paging, then field hints and the endpoint. Nothing is padding; even the endpoint line is a compact operational 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 parameterless-required, nested-criteria search tool with no output schema, the description covers scope, filter semantics, paging and field discovery. The main gap is the response shape — it is unclear whether 'Useful fields' are searchable inputs or returned attributes, which an agent must know without an output schema.

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 the baseline is 3. The description still adds value by naming concrete searchable fields (first_name, last_name, email, status, user_group_id) and clarifying the offset/limit/next_offset paging loop, though the AND-combination rule largely duplicates the schema's criteria description.

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 with scope: 'Search the users (staff) of the agency account.' It is unambiguously distinct from the many other rex_search_* siblings (contacts, listings, deals) and adds that returned user ids serve as agent/assignee/remindee ids elsewhere, which tells an agent exactly what this tool yields.

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 line 'User ids are used elsewhere as agent, assignee and remindee ids' gives a concrete when-to-use signal, and pointing at rex_describe_search_fields implies the field-discovery prerequisite. However, it never states when NOT to use it (e.g. vs rex_get_user_profile for a single user, or rex_autocomplete_contacts), so there is no explicit alternative routing.

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