search_notes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: case-insensitivity limited to ASCII, that results are drawn from a database snapshot, and that it returns previews and IDs rather than full bodies. It omits behavioral details like pagination/limit behavior, which the annotations do not cover.

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?

Four short sentences, no filler, with the core capability front-loaded and the routing hint placed after. Every sentence conveys distinct information (scope, matching semantics, return shape, exclusion inheritance).

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 no output schema, the description correctly states what comes back (previews and IDs) and where to get more (read_note). The remaining gap is parameter-level guidance for limit/offset/includeArchived, which is the only meaningful omission for a four-parameter search 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?

Schema description coverage is 0% across four parameters, so the description carries the full burden and does not meet it: limit, offset, and includeArchived are never explained, and only the query's case-insensitivity is touched on. 'Same exclusions as list_notes' obliquely gestures at archived filtering but requires cross-tool inference.

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 ('Search literal text in the Antinote database snapshot') and immediately scopes it as literal-only, which an agent can distinguish from semantic or full-text operations. It also names the sibling to use for full text, so the tool's identity is unambiguous among the six siblings.

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 routes the agent: 'use read_note for full text,' which defines the boundary between searching and reading. 'Same exclusions as list_notes' further ties it to the sibling's filtering semantics, though it does not spell out when to prefer search_notes over list_notes beyond that pointer.

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