reference_load

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions recursion and aggregation, offering some insight, but it does not disclose side effects, access control details ('allowed folder'), or whether the operation is read-only. The behavior remains underspecified for a tool that likely accesses files or resources.

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 a single sentence of about 15 words, front-loaded with the action 'Load' and the object. There is no wasted or redundant phrasing. It earns its place by stating the core purpose without unnecessary 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?

Despite having only one parameter and an output schema, the description leaves significant unresolved questions: what constitutes a 'text reference,' what 'matching allowed folder' means, and how recursive aggregation behaves. Given the existence of related tools and the domain-specific terminology, this is too terse to be complete for an agent seeking to invoke it correctly.

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 description coverage is 100%, with the sole parameter 'names' described as 'One to thirty-two unique relative paths in requested result order.' The description adds little beyond the schema, only echoing that these are 'relative paths' and that loading is 'recursive' and 'aggregated.' It does not clarify what 'names' refer to or how they map to references, but the schema already provides decent coverage.

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 uses a specific verb 'Load' and names the resource as 'recursive text references' with a scope ('every matching allowed folder'). It conveys what the tool does, though it does not explicitly distinguish it from sibling tools like reference_refresh or skill_load. The term 'text references' is somewhat ambiguous, preventing a perfect score.

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?

There is no guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or alternative tools. Sibling tools like reference_refresh and skill_load exist, but the description gives no context for choosing among them. Usage is only implied by the verb 'Load'.

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