Discover Note Paths

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

Annotations already establish readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuine behavioral detail beyond that: results are metadata-only (no bodies), an explicit ranking order (exact, then case-insensitive prefix, then other literal, then approximate), and the distinction between 'coverage' and 'truncated' as separate signals. It does not mention the fuzzy scan's candidate/time budget, though that lives in the schema.

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 opening clause front-loads the core purpose and the ranking rules follow in a compact, ordered sequence that mirrors actual result order. Every sentence carries information; the only slight drag is the coverage/truncated sentence, which reads as output-field plumbing though it is still relevant.

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 an output schema present, the description is not obliged to explain return values, and it correctly focuses on ranking, metadata-only scope, and the next-step call. The remaining gap is comparative placement among the many sibling search/listing tools, which for a vault with this many alternatives would be worth one extra clause.

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 six parameters are already documented in detail, including fuzzy edit-distance rules and limits. The description only contributes indirectly by framing fuzzy as 'optional typo matches' and tying 'coverage' to the approximate pass, which is marginal added meaning over the schema — baseline 3 applies.

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 ('Discover note paths') and immediately scopes it to path/metadata discovery rather than content retrieval ('Returns metadata without bodies'). An agent can distinguish it from read, but the description does not name what separates it from list_documents, browse_vault, or search, so it falls short of full sibling differentiation.

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 one explicit routing instruction — 'Use read with a returned path to retrieve its content' — which covers the natural follow-up call. However, there is no guidance on when to prefer this over search, list_documents, or browse_vault, and no exclusion conditions, leaving the main selection decision to inference.

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