mimicus_preview_references

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

Annotations say readOnlyHint=false and openWorldHint=true, and the description genuinely adds behavior beyond them: it will not click consent or access controls, owned cleanup is awaited before returning, and failures stop further batch admission. The 'no gallery media fetch or persistent cache' line is useful negative disclosure. It doesn't state auth prerequisites explicitly, so not a 5.

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?

Purpose is front-loaded and every sentence carries information, but the prose is dense and jargony ('actual MCP images', 'owned cleanup is awaited'), which slows parsing. No wasted sentences, but clarity-per-word is low.

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?

An output schema exists, so return-value detail is rightly omitted even though the description references fields like failureCode and executionStatus. Behavioral coverage is strong, but for a five-parameter nested-schema tool with 0% description coverage, the complete absence of parameter guidance leaves a real 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 description coverage is 0% with five parameters including a nested references array, so the description carries the full burden. It never mentions budgetMs, viewport, perReferenceTimeoutMs, or the reference object fields; 'bounded readiness waiting' only loosely gestures at waitForReadyMs and 'ordered' only hints at ordering.

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 verb is 'View' and the resource is 'individually authorized originals as ordered actual MCP images', which is specific enough to distinguish it from the analyze/compare siblings, but 'actual MCP images' and 'originals' are jargon that an agent may not decode reliably. The phrase 'before deep analysis' helps signal the tool's place in a pipeline without naming a sibling.

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?

'before deep analysis' implies a sequencing cue, but no alternative tool is named and no when-not condition is given. The sentence about 'transient loaders' implies use of waitForReadyMs but never says when to use this tool instead of mimicus_get_reference or mimicus_open_reference.

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