plan_multimodal_retrieval

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

The description adds 'without starting GPU training', which clarifies that this tool does not execute training—a behavioral trait beyond the readOnlyHint annotation. However, it does not mention what the tool returns (a plan) or any side effects, but the annotation already indicates read-only, so the bar is lower.

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, well-structured sentence that front-loads the core purpose. It is concise with no unnecessary words.

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 description covers the high-level purpose and constraint, but it does not describe the tool's output (a plan) or any return value. Since there is no output schema, this omission reduces completeness. Overall adequate but with a clear gap.

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 coverage is 100% with detailed parameter descriptions. The description does not add new semantic meaning beyond the schema; it merely aligns with the evidenceTypes parameter. Baseline 3 is appropriate.

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 the tool's purpose: plan a multimodal retrieval rollout for specific evidence types (screenshots, PDF pages, etc.) without starting GPU training. The verb 'plan' and resource 'multimodal retrieval rollout' are specific and differentiate it from other planning tools.

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 use for planning a retrieval system without GPU training, but it does not explicitly state when to use this tool versus siblings like 'plan_intent' or 'plan_context_footprint'. No alternatives or when-not-to-use guidance is provided.

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