VOMO

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

The annotations already establish that this is a safe, idempotent, non-destructive read with no open-world access. The description adds that the default response is the 'main smart note' while the alternate mode yields the full transcript, which is genuinely behavioral context. It is silent on what happens when the note is missing, how large a transcript can be, and whether transcript mode changes the response shape.

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?

It is a single compact sentence with the primary action front-loaded and the alternate mode trailing. Every clause carries information, though it is arguably under-specified rather than optimally concise.

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 a simple two-parameter read-only tool with an output schema, the description covers both operating modes. It omits failure behavior for unknown note IDs and any notion of what 'smart note' contains versus a transcript, leaving modest gaps for an agent deciding between modes.

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?

The schema already documents both parameters fully: note_id is '笔记 ID', and transcript is '是否返回转录'. The description's 'or return full transcript' restates the transcript flag's effect and adds the notion of a 'main smart note', but it gives no additional semantics such as transcript size, pagination, or fallback behavior. A baseline of 3 is appropriate given 100% schema coverage.

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 states a specific verb and resource (read the main smart note by note ID), and it also names a second mode (return the full transcript). This is clearly distinct from the list-style sibling notes_list, but it does not distinguish the tool from search. Overall, it is clear but not fully differentiated from 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?

The phrase "by note ID" implies that the tool is for known-ID lookup rather than discovery, and the transcript clause hints at when the alternate mode applies. However, the description never says when to use this tool versus search or notes_list, and it does not name any prerequisites or exclusions. The guidance is only implied.

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

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

The annotations already establish read-only, idempotent, and closed-world semantics, so the description's main value is the pagination invariant that filters must remain the same across pages, which nothing in the structured fields states. Current-user scoping is also useful and not visible 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?

It is a single compact sentence with the ordering and scope front-loaded, followed by the filter families and the pagination rule. Every clause carries information, though the pagination clause is slightly compressed.

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?

The output schema covers the return-value shape and the annotation set covers the safety profile, so the description only needs to convey what is listed and how filtering and paging behave, which it does. Minor gaps remain, such as the absence of guidance on how filters interact.

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% and each parameter carries its own description (limit, scope, since, cursor, folder, folder_id), so the schema does the heavy lifting. The description only summarizes the filter families and adds no format or interaction detail beyond that.

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 gives a concrete verb plus resource (列出/笔记摘要), adds ordering (按新建顺序) and scope (当前用户的), which distinguishes it from the single-item sibling notes_get. It stops short of explicitly contrasting itself with the 'search' sibling, e.g. by saying keyword lookup belongs there.

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 states the supported filters (收藏、文件夹、创建时间), so the intended browsing use case is implied, but it never says when to prefer notes_get or search instead. An agent must infer the division of labor from sibling names alone.

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

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

Annotations already establish read-only, idempotent, and non-destructive behavior. The description adds useful behavioral detail beyond annotations: case-insensitive full-keyword matching, current-user scope, title-hit priority, and update-time ordering. It still does not cover pagination or result-shape details, but the output schema covers those.

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?

A single front-loaded sentence with no filler; it conveys scope, matching rule, and result ordering efficiently.

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 annotations and an output schema present, the description supplies the key search semantics an agent needs: scope, match rule, and ranking. Minor ambiguity remains around the transcript toggle and when to prefer this over sibling tools, but it is largely complete.

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 the schema already documents query, limit, cursor, and transcript. The description only repeats the query's case-insensitive full-keyword semantics and adds no parameter-level guidance beyond that, matching the baseline of 3.

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 names a specific operation (keyword matching) and target set (the current user's titles, smart notes, transcripts), with ranking rules. It does not explicitly compare against notes_get or notes_list, so sibling differentiation relies on the tool name and stated scope rather than explicit text.

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 description states what matching behavior occurs but gives no when-to-use or when-not-to-use guidance. An agent is not told when to choose this search tool over notes_list or notes_get.

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