Semantic Search

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

Annotations already declare readOnlyHint=true and idempotentHint=true, informing the agent of safety and idempotency. The description adds valuable context about embedding the query, scoring chunks, and deduplication, which goes beyond the structured annotations.

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 sentences packed with essential information, front-loading the core functionality and including critical usage guidance. No wasted words.

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?

Despite lacking an output schema, the description explains the deduplication behavior and recommends get_note for full bodies. It references prerequisites (index_vault) and sibling tools, providing a complete picture of how this tool fits into 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 the schema already documents each parameter thoroughly. The description adds overall context but does not provide significant additional meaning for individual parameters beyond what is in the schema.

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 performs semantic search by meaning, uses embedding and cosine similarity, and deduplicates to one hit per note. It distinguishes itself from sibling tools like index_vault and get_note, making its purpose unambiguous.

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 states that index_vault must be run first to populate the index, clarifies that auto-indexing is not performed due to cost awareness, and recommends pairing with get_note to retrieve full note bodies after selecting a hit.

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