Search by Property

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

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, but the description adds substantial behavioral context beyond them: unknown key/unmatched value returns an empty array rather than an error, and truncation is unobservable (exactly `limit` results may mean more exist). The mtime sort order with the caveat that recently-synced notes can sort ahead is also disclosed.

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, two concrete invocation examples, and clear section headers (When to use / Parameters / Errors / Returns), which makes it scannable. The numeric-matching paragraph is dense and somewhat over-explained, but every section is doing real work for correct invocation, so it is not padding.

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?

No output schema exists, so the description carries the return contract itself — field list, descending-filesystem-mtime ordering, and the conditional leading_callout / additional_properties fields. Combined with error behavior and matching semantics, an agent has everything needed to call and interpret this tool.

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?

Although schema coverage is 100%, the description goes well beyond the schema: exact and case-sensitive key/value matching, the finite-YAML-number numeric matching rules (including edge cases like 2^53 and '1e-999'), checkbox handling as '1'/'0', full-element array matching, folder subfolder inclusion with ASCII case-insensitivity, and the limit-keeps-most-recent semantics. This is meaning an agent cannot derive from the schema alone.

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 ('Find notes where a frontmatter property matches a value') and immediately narrows scope ('metadata-only search, no text query needed'). It explicitly distinguishes itself from vault_search and vault_search_by_tag, so an agent can select it 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?

Provides an explicit 'When to use' line plus named alternatives with the conditions that select them: prefer vault_search when a text query exists, prefer vault_search_by_tag for tag/hierarchical queries, and use vault_list_property_keys/values for discovery. This is exactly when-and-when-not guidance.

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