hydra_render

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

Beyond the annotations, the description discloses crucial runtime behavior: all outputs keep rendering regardless of visibility, so chains can still feed hidden outputs. It also states clearly that the tool does not change the document, which is important for an operation where readOnlyHint is false and destructiveHint is false. This prevents the agent from assuming the choice persists.

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?

Three compact sentences deliver the action, parameter values, runtime implications, and the permanence boundary with zero filler. The most important information appears first, and the example of chaining o1 to o0 earns its place by illustrating why continued rendering matters.

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?

For a single-parameter display tool, the description is complete: every accepted value, the behavioral nuance of continued rendering, and the distinction between transient and permanent are all covered. The presence of an output schema means return-value details need not be restated in the description.

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?

The input schema provides only a bare `output` string with no enum and no description (0% coverage), so the description carries the full burden. It fully compensates by listing every valid value and explaining the visual result for each, including the "all" grid case. This is exactly what the schema lacks.

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 opens with a specific action and target: showing an output full-screen or all four outputs in a grid. It enumerates the exact accepted values ("o0", "o1", "o2", "o3", "all"), which distinguishes this display-routing tool from the broader hydra sibling set. Nothing about it is vague or tautological.

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 gives clear when-to-use context: this is for choosing what is visible while rendering continues, not for making a permanent document change. It explicitly names the alternative path for permanence by writing `render(o1)` in a block, which tells the agent when this transient tool is appropriate versus a persistent block-based approach.

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