Inline preview (snapshot)

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

Description states 'Read-only one-shot inspection', aligns with readOnlyHint annotation. Adds behavioral details like parent error sweep BFS, thumbnail size and lossy nature, and scope of parameters. No contradiction with annotations.

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?

Four sentences, each serving a purpose: first defines the tool's output, second gives use case, third provides alternative, fourth specifies thumbnail quality. Front-loaded and efficient.

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?

Covers all aspects: what the tool does, what it returns (thumbnail, errors, params, stats), when to use, parameter details, and output quality. Output schema exists, but description still sufficiently explains the return payload.

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?

With 100% schema coverage, baseline is 3. Description adds meaning by explaining the purpose of each parameter (e.g., format selection impact on payload size, parent_depth for error sweep hops, max_changed_params for top-N defaults). This goes beyond the schema descriptions.

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 it performs a read-only inspection of a TOP, returning a thumbnail, error sweep, parameter changes, and cook stats. It distinguishes itself from sibling tools like get_preview and get_td_node_errors by emphasizing it is for quick health checks.

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?

Explicitly says 'One call instead of chaining get_preview / get_td_node_errors / get_td_node_parameters' and advises using get_preview/render_output for delivery-grade frames. Provides clear when-to-use and when-not-to.

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