Search notes

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

With no annotations, the description carries the disclosure burden, and it does state what comes back (matching blocks, IDs, document paths) — useful because there is no output schema. It never states the read-only nature or result paging behavior, but for a search tool the safety profile is clear from the wording.

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 sentences, all load-bearing: purpose and return shape first, usage context second, syntax third. No filler and the most important information is front-loaded.

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?

Covers what the tool does, when to reach for it, what it returns, and how to form queries — enough to call it correctly given no annotations and no output schema. Only minor gaps (result ordering, paging guidance) remain, and paging is already partly covered by the schema.

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 baseline is 3, and the description adds genuine value beyond the schema by documenting SiYuan query syntax (AND, quoted phrases, OR, negation, wildcard) that an agent could not infer from 'Search keywords.'

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+resource ('Full-text search across the workspace') and goes further by describing the result shape ('matching blocks with their IDs and document paths'). This distinguishes it clearly from retrieval siblings like get_document, get_block, and sql_query.

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?

'Use this to locate content before reading or editing it' gives a clear when-to-use context that positions it ahead of the read/edit siblings. It stops short of naming an explicit alternative (e.g. sql_query for structured queries) or stating when-not to use it, so it falls just short of the top score.

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