pixelcue_keywords

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

The annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is structured already. The description adds real value with "explicit opt-in permits inference/model caching," disclosing that inference and caching are gated behind allow_inference rather than automatic. However, it does not say where tags are written (file metadata vs sidecar) or what happens when inference is declined, which matters for a non-read-only 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?

A single front-loaded sentence with no filler and zero redundancy. Its brevity is arguably a liability, but nothing in it wastes space.

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 values need not be described, and annotations cover the safety signal. Still, for a mutating three-parameter tool with zero schema coverage, the definition leaves key operational questions open: tag destination, behavior when opt-in is false, and model selection tradeoffs.

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% and no parameter has an enum, so the description carries the full burden. It maps loosely to all three: "explicit opt-in" gestures at allow_inference, "model caching" at model, and "one local media file" at path — but it never explains accepted model values, defaults, or the behavioral difference between allow_inference true and false. The hints are suggestive rather than instructive.

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 gives a specific verb+resource: "Tag one local media file through PixelCue," with an explicit scope of a single local file. This lets an agent distinguish it from batch or analysis siblings such as pixelcue_visual_analysis. It falls short of 5 because "tag" is never elaborated as keyword extraction, despite the tool name.

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?

There is no when-to-use, when-not-to-use, or alternative routing guidance against the many sibling tools (pixelcue_visual_analysis, pixelcue_health, keywordmoves_run). The "one local media file" phrasing implies single-file local input only, but this is inference rather than stated guidance.

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