diana_community_prepare

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

Annotations only declare openWorldHint=false, so the description carries most of the behavioral burden. It does add genuinely useful context — that copies are redacted, local-only, and never uploaded — which corroborates rather than contradicts the annotation. It omits where the copies are written, whether existing files are overwritten, and whether any source entries are modified.

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?

Two clauses for the purpose, then a compact Args block, each line carrying non-redundant information. Safety-critical scope ('local-only', 'never upload') is front-loaded and nothing is padded.

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 two-optional-parameter tool with an output schema, the description covers the purpose, the safety envelope, and both parameters' semantics including their interaction. The only meaningful gap is where the prepared copies land and what the agent should do next with them, which the output schema may partly cover.

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, and it does: entry_ids is explained as exact private experience ids plus the selection rule when omitted, and recommended_only is explained as a filter applied only when entry_ids is omitted. The conditional interaction between the two parameters is the key semantic and it is stated explicitly.

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 specific verb and resource: 'Create local-only redacted copies of private experience entries for human review.' That is far more concrete than the tool name alone and makes the redaction/local-only nature unmistakable. It stops short of naming which sibling (e.g. diana_community_contribute or diana_community_preview) this replaces, so it doesn't fully differentiate.

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?

'For human review' and 'never upload them' imply this is the pre-contribution inspection step, which gives an agent usable context. However, no explicit when-to-use versus when-to-use-an-alternative guidance is given, and it never names a sibling tool as the alternative step.

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