Recall past prints of this model

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

Beyond the readOnlyHint annotation, the description discloses substantial behavioral details: geometry-first matching, fallback to model_name when the slicer is offline, returning available=false when no outcome store exists, and the dangerous fallback of returning recent prints of ANY model with matched_by='recent' while warning never to attribute them to the current model. This is exactly the kind of edge-case transparency that helps an agent avoid misuse.

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 description is longer than average but every sentence adds meaningful information about matching, return values, timing, and fallback behavior. The 'Read-only.' sentence is redundant with the annotation, but the overall structure is dense and front-loaded with the core purpose.

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 read-only tool with two optional parameters and no output schema, the description covers the main call context, return content, and important edge cases. The only notable omission is the effect of the limit parameter on the number of returned prints, and there is no explicit mention of the output structure beyond listing fields.

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 schema description coverage at 0%, the description compensates for model_name by explaining it is used when the slicer is offline and for matching. However, the 'limit' parameter is not explained at all, leaving its behavior to inference from the default value. Partial compensation only.

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 the tool recalls past prints of the current model, matching by geometry or model_name and returning results, verdicts, and settings. It is specific about the resource and action, though it does not explicitly name sibling tools like 'remember' to differentiate them.

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 explicitly says 'Call this BEFORE slicing', giving a clear temporal context for when to use the tool. It does not, however, mention alternative tools or when not to use it, so it stops short of full exclusions and alternative routing.

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