query_notes

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

Annotations already carry readOnlyHint=true, so the description correctly adds no mutation warnings and instead discloses a non-obvious behavioral contract: results are compact rows (path + title by default, extensible via select) and never the note content itself. This materially changes what an agent expects to receive and is not stated in the annotations. The only missing behavioral context would be pagination/size caps beyond the schema limit parameter, but the schema already covers that.

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?

Three short sentences, each earning its place: scope definition, return-format contract, and sibling routing. The most distinguishing trait (metadata vs content) is front-loaded, and nothing is wasted restating annotations or schema defaults. It is unusually economical for a tool with 11 parameters.

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 an 11-parameter read-only tool with a 100%-covered schema, the description covers purpose, filter dimensions, result shape, and the main sibling alternative; the output-schema absence is compensated for by the explicit 'returns compact rows, not note content' statement. The only marginal gap is that it doesn't mention distinguishing siblings like list_notes or get_tags, and the sort/select defaults are left to the schema. An example 'where' predicate would be nice but is not a genuine completeness gap.

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 documentation covers 100% of the 11 parameters, each with a meaningful description, including defaults for select and sort and the AND semantics of where. The description only echoes the filter axes (tag, folder, modified time, size) and the select default, with no syntax or format details that the schema lacks. Per the high-coverage baseline, the description adds no real param-value meaning, so a 3 is appropriate.

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 opens with a specific verb and resource ('Structured metadata query') and enumerates the exact filter dimensions: frontmatter key/value predicates, tag, folder, modified time, and size. It also distinguishes itself by declaring that it returns compact rows rather than note content, which clearly separates it from content-returning siblings like read_note and search. An agent can tell what this does and is not without reading 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?

The final sentence explicitly routes usage: 'Use this instead of search when filtering by properties rather than text.' It names the alternative sibling and gives the classification condition, effectively covering both the when (property-based filtering) and the when-not (text-based filtering). This is explicit routing guidance, not just implied context.

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