diana_experience_mine_logs

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

With no annotations, the description carries the full burden and does well: it discloses that drafts are unverified, attributed to historical logs, require explicit user approval before promotion, that a re-run only refreshes existing statistics, and that one run produces a single git commit. SSH handling is also covered, including temporary-file parsing and no local storage. It does not address permissions or runtime cost, which keeps it from a 5.

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 what-and-how is front-loaded in the first sentence, with consequences (unverified drafts, approval workflow) following. The Args block is clean, though the prose is somewhat dense and slightly overlong for two parameters.

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-parameter mining tool with an output schema already documenting return values, the description covers creation semantics, verification status, approval flow, idempotent re-run behavior, git commit granularity, and SSH privacy handling. Nothing an agent needs in order to call it correctly is missing.

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 0%, so the description must compensate, and it does: folders accepts absolute paths, is searched recursively, also accepts individual .out files, and supports ssh://user@host/absolute/path with remote-path recording. dry_run is explained as report-only with no creation.

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 uses a specific verb and resource: scan every .out file under the given folders and draft one experience entry per DIANA message kind. That distinguishes it from manual entry tools like diana_experience_add or diana_read_out, though no sibling is named explicitly.

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?

Usage is implied rather than stated: mine historical logs, then when the same message recurs in real work, propose the draft for approval as new evidence. It says re-running only refreshes statistics, which hints it is not for editing entries, but it never explicitly says when to prefer diana_experience_add or diana_experience_update instead.

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