Corpus Triage

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

With no annotations at all, the description carries the full burden and discloses almost nothing: it does not say whether scoring is a read-only evaluation or writes artifacts into deck_dir, whether it consumes model calls or incurs cost, or how long it takes. The presence of an output schema excuses explaining return values, but the side-effect and cost profile remains a real gap for a tool that takes an absolute deck path.

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?

Two short sentences, front-loaded with the purpose, and no filler. The second sentence largely duplicates what the schema already states about the text/label choice, so a small amount of the text does not earn its place.

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?

The tool sits in a dense pipeline (corpus_load, corpus_digest, topic_triage_calibrate) and takes a deck directory, but the description never explains where triage fits in that flow, what happens to the scores, or what the deck_dir is used for. With no annotations and no behavioral detail, an agent would have to guess its role in the workflow.

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 100%, so all three parameters are already documented, including that 'text' takes priority over 'label'. The description restates that duality ('inline text or a stored label') without adding format, size, or validation details, which is the expected baseline when the schema does the heavy lifting.

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 uses a specific verb+resource combination ('Score source material for flashcard potential'), so an agent knows it evaluates input against flashcard suitability. It stops short of naming how it differs from neighbors like corpus_digest or topic_triage_calibrate, so sibling differentiation is left implicit.

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?

'Pass inline text or a stored label' is input guidance rather than usage guidance; it implies the two modes of invocation but never says when to prefer this triage step over corpus_digest or corpus_coverage. There are no exclusions or preconditions (e.g. whether a corpus must be loaded first), so usage is inferred rather than stated.

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