lore_profile

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

Annotations declare destructiveHint=true and idempotentHint=false, and the description substantiates that with concrete consequences beyond the annotations: every call regenerates and replaces the existing profile, an active profile regresses to pending and blocks downstream steps, status=needs_model fires 1-3 times and nothing is persisted until answered via lore_resume, and the language is locked after base generation. This is rich, non-obvious behavioral disclosure.

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?

Front-loaded with purpose on the first line, then the workflow, then the state-machine warnings. It is dense and long, but for a multi-step, stateful tool nearly every clause carries decision-relevant information, so little is expendable.

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?

With 7 params, a nested object, no output schema, and a complex review/resume/decide state machine, the description covers what a caller needs: the persisted artifact, the designReview contents (accumulated decisions plus up to 5 open questions), the needs_model/resume loop, and the conditions for finalization.

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 coverage is 100% so the baseline is 3, but the description adds workflow meaning beyond the schema: brief doubles as the basis for the reading-difficulty answer, feedback is described as accumulating the prior round's question answers into design decisions, and mode's effect on saved state is tied to the overall flow. It layers semantic context on top of the already-documented parameters.

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 precise verb+resource: compiling the interview brief into a StoryProfile and persisting it to .vibelore/story-profile.json, and enumerates the profile's contents. It distinguishes itself from siblings by naming lore_profile_decide (finalization) and lore_resume (model answers), so an agent can route without opening any schema.

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?

Explicit when/when-not/alternatives: always show open questions, pass answers as feedback, re-invoke; confirm via lore_profile_decide only when no questions remain or the user approves; use mode=auto only when the user says 'just do it'. The alternative tool and its trigger condition are both named.

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