gc_find

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

With no annotations provided, the description carries full burden. It's a read/search operation by nature ('find documents'), which is safe, but it doesn't disclose behavior like whether this is a full-text search or metadata-only, result ordering, or pagination semantics beyond the limit default. The title-substring LIKE hint in the param schema adds some behavior info, but the description itself is thin on behavioral detail.

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?

Single efficient sentence that front-loads the purpose. Zero waste. Could benefit from an example but remains appropriately 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 find/search tool with 5 optional parameters and no required fields, the description is adequate but not complete. It doesn't explain which filters are combinable, how to construct effective searches (partial vs exact matches), whether domain/project/type are exact or substring matches, or what the result set looks like. With no output schema and no annotations, the description could reasonably do more, though the tool is plausibly simple enough that this is near-minimum-viable.

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 baseline is 3. The description lists the filter dimensions (domain, type, project, title) which confirms what the schema already documents. It adds marginal framing (these are metadata filters) but doesn't provide format examples, combinational semantics (AND vs OR), or how filters interact.

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?

Clear verb+resource ('find documents') with specific filter dimensions listed (domain, type, project, title). It distinguishes from siblings like gc_recall (likely recall/retrieve) and gc_retain (store) by clearly indicating this is a metadata-driven search, though it doesn't explicitly name alternatives.

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 implies usage as a metadata search tool but doesn't state when to prefer it over gc_recall or gc_docs. With over 60 sibling tools including some document-related ones (gc_docs, gc_recall, gc_obsidian_vault), explicit differentiation would strengthen this dimension.

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