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

Goes well beyond the annotations by disclosing a privacy guarantee ('the pictures never reach Rapier's server') and explaining the two execution paths and that results are saved by the person in the view. The annotations already flag non-readOnly, non-destructive, closed-world behavior, and the description adds the fallback-link behavior that an agent must anticipate. Minor omission: it doesn't say what the link-fallback response payload looks like beyond 'answers with the link'.

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 purpose and the privacy guarantee are front-loaded, and the parameter notes are compactly packed into the final sentences. The middle clause 'in this app's view where the app can show one' is awkward and slightly redundant, but no sentence is genuinely wasteful.

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 five-parameter tool with no output schema and non-readOnly annotations, the description covers the operation, both delivery modes, the privacy model, and the tuning knobs with defaults. An agent has enough to decide when to call it and what to pass.

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 only 20%, so the description must carry the load, and it does for the three meaningful parameters: files is 'the chat's pictures' with omitting meaning person-picks, quality is lossless/high(default)/medium, and effort is 1-9 with default 7 and 'higher is smaller and slower'. The agent and operation_id parameters get no explanation, which keeps this from a 5.

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?

States a specific verb and resource plus format and directionality: 'Convert pictures to JPEG XL, or JPEG XL back, on the person's own device.' This is clearly distinguishable from siblings like edit, export, show, and open, which do not mention format conversion or the on-device Rapier view.

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?

Gives real conditional guidance: when a view is available the conversion happens in-app, and without a view the tool returns the https://rapier.website/jxl link instead. It also tells the agent to omit files to let the person pick them. It never explicitly contrasts with sibling tools such as export or edit, so a small gap remains.

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