gflow_instructions_add

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

With no annotations, the description carries the full behavioral burden bound. It discloses that the operation is persistent, credits-free, and that refs are classified automatically with a side-effect of uploading local image paths. It does not mention permissions, idempotency, or failure modes, but it covers the most non-obvious behaviors.

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 two sentences of zero-waste prose. The first sentence front-loads the action and context, and the second uses a compact arrow format to explain ref classification. Every sentence contributes new information.

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?

The tool is simple, has an output schema, and its required parameter names are largely self-explanatory. The only genuinely obscure parameter behavior, refs, is explained well. Minor gaps such as what exactly 'project' and 'profile' accept prevent a perfect score, but the description is adequate for invoking the 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?

Schema description coverage is 0%, so the description must compensate. It thoroughly explains the refs parameter's classification rules, but does not add meaning for project, title, text, enabled, or profile beyond their names and defaults. For a six-parameter tool, one parameter of explanation is not sufficient.

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 states a clear verb and resource: 'Add a persistent instruction card to a Flow project's Agent-Mode brief.' It also distinguishes itself from media-generation and instruction-management siblings by emphasizing persistence and the credits-free property. An agent can understand exactly what this tool contributes.

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 'Add...' phrasing implies the intended use case, and 'persistent' and 'Agent-Mode brief' give helpful context. However, the description never explicitly names alternatives or conditions such as 'use this instead of gflow_instructions_apply when...'. Selection guidance is left mostly to inference from sibling tool names.

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