Search Notes

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

With no annotations, the description carries the behavioral burden. It discloses the local-mirror dependency, the sync prerequisite, and the return semantics ('score (100 = exact substring)' and 'whether it hit the description or the note'). It stops short of describing ordering or filtering behavior, but the output schema covers return structure.

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 front-loaded with the core purpose, then gives use guidance, concrete examples, return behavior, and a prerequisite in three compact sentences. No sentence is filler.

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 search tool with one required parameter and an output schema, the description covers the key invocation context: fuzzy behavior, the local mirror, sync requirement, and the two match targets. It could name search_expenses explicitly, but the 'exact search misses' phrasing makes the alternative clear.

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 0%, so the description must add meaning. It clarifies the query semantics thoroughly (typos, abbreviations, buried amounts/words) and explains the score scale, which gives meaning to min_score. However, limit and include_deleted are left to inference from their names/defaults.

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 opening line names a specific verb and resource: 'Fuzzy search over expense descriptions AND notes/details in the local mirror.' It differentiates from siblings by explicitly framing this as the fallback when 'exact search misses' and by covering note details as well as descriptions.

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?

It gives an explicit trigger condition: 'Use when exact search misses — catches typos, abbreviations...' and gives examples of buried matches. It also states a prerequisite ('Run sync_all first'), so the agent knows the required precondition.

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