AroFlo MCP

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

The annotations indicate read-only, idempotent operations, which align with the 'Query' and 'GET' description. The description adds substantial behavioral context not in annotations: the pipe-delimited WHERE clause syntax ('and|field|=|value'), ORDER syntax ('field|asc'), and JOIN areas ('lineitems'). It also documents the external resource pattern ('aroflo://docs/api/<slug>') for field validation, clarifying the open-world nature.

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?

The description is four dense sentences with zero waste. Information is front-loaded (purpose first), followed by syntax examples, configuration options, and documentation references. Every sentence earns its place by conveying critical syntax patterns required to construct valid API calls.

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?

Given the high complexity (18 parameters, nested objects) and presence of an output schema, the description appropriately delegates field-level documentation to the external resource reference ('aroflo://docs/api/<slug>'). It provides sufficient context for the query DSL. Minor gap: it doesn't clarify the relationship between the 'mode' enum and the separate boolean verbose/debug/raw flags.

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?

With 0% schema description coverage, the description must compensate. It successfully documents the complex query syntax for 'where', 'order', 'join', and explains 'mode' options, 'compact', and 'select'. However, it leaves many of the 18 parameters unexplained: the pagination controls (page, pageSize, autoPaginate, maxPages), the confusing overlapping 'maxResults'/'maxItems'/'maxItemsTotal', the 'extra' object, and the relationship between the 'mode' enum and the separate boolean flags (verbose/debug/raw).

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 description opens with 'Query the AroFlo Users zone (GET)', providing a specific verb (Query), resource (Users zone), and HTTP method context. The explicit mention of 'Users zone' effectively distinguishes this tool from the numerous sibling get_* tools for other zones (tasks, quotes, assets, etc.).

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?

Usage is implied by the specific zone mentioned ('Users zone'), indicating it retrieves user data. However, it lacks explicit guidance on when to use this specific zone getter versus the generic 'aroflo_query_zone' tool or when to prefer it over 'aroflo_get_record' (singular). It also omits guidance on pagination strategy (autoPaginate vs manual page iteration).

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