recall

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

No annotations exist, so the description carries the full behavioral burden. It does disclose two useful traits beyond the schema: results are ranked by relevance descending, and the caller needs note.recall.read scope. It omits read-only confirmation, what a result item contains, and any limits on corpus or latency.

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 front-loaded statements: what it does, when to use it, result ordering, and the auth requirement. No filler, though the scope sentence and the ordering sentence could be merged for tighter structure.

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 must describe return values; it only says results are sorted by relevance and never describes the shape of a hit (note ID, title, snippet). Given a four-parameter tool with a mode enum, this leaves an agent guessing about the response.

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 coverage is 100%, so query, top_k, response_mode, and max_snippet_chars are already fully documented in the schema. The description adds no parameter-level detail such as query length, when to set response_mode=snippet, or the interaction between snippet mode and course filtering, so it stays at the baseline.

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: global semantic recall across all notes, plus the concrete query intent. It is clearer than the sibling list_notes/get_notes by scope (global) and by method (semantic), but it never names a sibling or explains how it differs from recall_knowledge, which is the most confusable neighbor.

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 two example phrases ("搜一下", "找找哪些笔记提到了 XX") imply when to reach for it, which is real guidance. However, there is no explicit exclusion, no mention of when to use recall_knowledge or plain listing instead, and no guidance on choosing top_k or response_mode.

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