AroFlo MCP

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

Annotations declare readOnlyHint and idempotentHint, but the description adds valuable implementation context by disclosing the dual-strategy approach: 'direct WHERE filters where supported' versus 'bounded scanning where necessary.' This explains the tool's performance characteristics and justifies the existence of the max*Scanned parameters without contradicting the read-only safety annotations.

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 consists of exactly two efficiently structured sentences. The first front-loads the core purpose and input options, while the second provides critical implementation context. No words are wasted; every clause serves either functional specification or behavioral transparency.

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 tool's complexity (18 parameters, multiple entity types, fallback scanning logic), the description adequately covers the primary use case but leaves significant gaps regarding secondary parameters and output structure. However, since an output schema is present, the description appropriately avoids redundantly explaining return values, keeping it minimally viable for a complex resolver 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?

With 0% schema description coverage, the description bears full responsibility for parameter documentation but only explicitly mentions 5 of the 18 parameters (the starting identifiers). It fails to explain the date filters (quoteSinceCreatedDate, taskSinceDateRequested), inclusion flags (includeQuoteLineItems), output modes, or pagination controls, leaving the majority of parameters semantically undocumented.

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 clearly defines the specific action ('Resolve') and resource ('job context'), explaining that it connects job numbers with related tasks, quotes, and projects. It effectively distinguishes this tool from the numerous simple 'get' siblings (e.g., aroflo_get_tasks, aroflo_get_quotes) by positioning it as a cross-referencing resolver rather than a direct entity fetcher.

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 lists the five valid starting identifiers (jobNumber, quoteId, quoteRefno, projectId, projectRefno), providing clear input guidance. However, it fails to explicitly state when to use this resolver versus the simpler direct getters (like aroflo_get_tasks) or when the bounded scanning fallback might be triggered, leaving usage implications largely implicit.

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