prepare_visual_qa_fix

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

With no annotations, the description carries full burden. It explicitly states 'No LLM call.', which is a key behavioral trait. It discloses that the tool returns a fix prompt, response schema, and images, and that the agent must generate full slide spec JSON before calling the ingest 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?

The description is concise, around 10 sentences, front-loaded with purpose and key return info. The 'Args' section is well-formatted. It could be slightly more structured by separating input and output, but it's efficient and readable.

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 4 parameters, no annotations, and an output schema (not shown), the description covers inputs, outputs, and workflow context (next step). It mentions the return structure but does not detail the output schema fields, which is acceptable since output schema exists. Minor gap: no mention of prerequisites or errors.

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 does: each parameter is explained with context (e.g., 'issues_json: JSON array of issues from ingest_visual_qa_analysis', 'slide_index: 1-based slide position', 'iteration: Iteration counter matching the capture'). This provides full semantics beyond the bare schema.

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 states 'Prepares the fix task for a slide with detected issues.' It uses a specific verb (prepares) and resource (fix task for a slide), and implicitly distinguishes from the sibling tool 'ingest_visual_qa_fix' by explicitly instructing to call that tool afterward.

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 implies usage after 'ingest_visual_qa_analysis' through the 'issues_json' argument, but does not explicitly state when to use this tool versus other prepare tools like 'prepare_visual_qa_analysis'. It provides the next step but not alternatives.

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