remarkable_search

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds significant behavioral detail beyond that: it explains the two execution modes (metadata-only without grep, content search with grep), the use of a cached FTS5 index, that reading via remarkable_read populates the index, that the response includes index_coverage, and the 10-document limit. It also notes 'no cloud downloads' in metadata mode. No contradiction with annotations.

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?

The description is well-organized with sections: usecase, instructions, parameters, examples. It is reasonably concise and front-loaded with the core purpose. There is minor redundancy (limits and parameter default repeated, 'Use grep' mentioned twice), but overall it is efficient and easy to scan. The examples are helpful.

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 tool with 5 parameters, an output schema, and read-only annotations, the description covers the main behavioral aspects: modes, indexing, limits, and examples. The output schema handles return values, so index_coverage is mentioned but not detailed. The main gap is the undocumented compact_output parameter, which prevents full completeness. Also, it doesn't mention pagination or sorting, but those are not critical for a search tool of this size. Overall, it is fairly complete with one notable omission.

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%, so the description must compensate. It explains query, grep, limit, and include_ocr with meaningful descriptions (e.g., grep is 'Optional regex pattern to search within document content'). It adds max=10 for limit, which the schema lacks. However, it completely omits compact_output, a fifth parameter, leaving the agent with no guidance on what it does. Since it covers 4 of 5 parameters but misses one entirely, it does not fully compensate for the lack of schema descriptions.

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 clear use case: 'Search across multiple documents and return matching content.' It specifies the verb (search), the resource (multiple documents), and the outcome (matching content). It further distinguishes two modes (metadata-only vs. content grep), which sets it apart from sibling tools like remarkable_browse (browsing) and remarkable_read (reading). No ambiguity about what this tool does.

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 clearly implies when to use this tool: when you need to find documents by name or indexed content. It explains the relationship with remarkable_read (reading indexes content for future search), which is useful context. However, it does not explicitly state when to prefer this over alternatives like remarkable_browse or remarkable_recent, nor does it mention exclusions. It provides clear context but not explicit when-not guidance.

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