Read a register (cost centres, contracts, partners, …)

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

With no annotations, the description carries full burden. It discloses auto-pagination, query/sort support, and typical entry fields, which adds value beyond the name. However, it does not mention error handling, permissions, or result count limits, leaving gaps for a read tool.

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?

Description is two sentences plus an example; the long type list is informative but slightly redundant with the schema enum. Overall efficient and front-loaded with the core purpose.

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 read-only tool with no annotations and no output schema, the description covers main behaviors (auto-pagination, query/sort, typical fields) but omits edge cases like onlyValid semantics, maxItems behavior, and error responses. Moderate completeness.

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 covers 50% of parameters (type, query, onlyValid). The description adds an example combining query and type, and mentions typical response fields, which helps parameter understanding. But it does not clarify sort, maxItems, or organization, so compensation is only partial.

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?

Description clearly states 'Read entries from any wflow register/reference table', using the specific verb 'Read' and resource 'register/reference table'. It distinguishes from sibling getters (like get_team, get_user) by listing 24 register types, making the exact scope unambiguous.

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?

Provides clear usage context: this is for reading from registers/reference tables, with an example showing how to resolve a cost centre. It does not explicitly mention when not to use or alternatives, but the scope is self-evident.

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