Propose facts from a note

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

With no annotations, the description carries the burden and does substantial work: it discloses the engine's auto-accept rules (frontmatter, `key:: value`, `- [key] value`), why prose formatting is surfaced instead of assumed, and that only facts NOT yet stored are returned. It never explicitly states whether the call mutates the vault/index or requires auth, which is a gap for a tool feeding a write pipeline.

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 the core purpose, then the mechanism, then the action. The closing line ('This keeps judgement with you and out of the index') is motivational rather than operational, so it burns a little space, but the rest is dense and informative.

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 two-param read/surface tool with no output schema and no annotations, the description covers what is returned, why some content is surfaced rather than auto-accepted, and the follow-up action. Only the limit parameter and the explicit side-effect/auth profile are left unaddressed.

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 50%: notePath is documented in the schema, limit is not. The description implies single-note vs. vault-wide sampling ('a note's structure' ... 'sample the vault') which aligns with notePath, but it says nothing about limit or how many candidates are returned by default. It partially compensates but does not close the coverage gap.

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: returns candidate facts mined from a note's structure that are not yet in the fact store. It clearly distinguishes itself from the write-side sibling lore_assert_fact by framing itself as the adjudication/surfacing step.

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?

Explicitly routes the agent: review the returned candidates and call lore_assert_fact for the ones that are genuinely durable facts. It also explains why prose formatting lands here rather than being auto-accepted, which tells the agent when this tool's output is worth acting on.

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