diana_experience_verify

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

With no annotations supplied, the description carries the full burden and does so well: it discloses the isolation model (short-lived batch DianaIE, never the user's live session, empty temp WORKDIR), the pass criterion (no exception, use assert), side effects (results written to each entry's checks field, failures marked disputed, one git commit per run), and the licensing cost (a seat for ~15 s plus script run time). These are exactly the operational facts an agent cannot get from the schema.

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 purpose and trigger are front-loaded, then behavior, then args — a sensible order with no filler sentences. The behavioral paragraph is dense and long-winded in places (parenthetical asides about WORKDIR), which slightly hurts scanability.

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 mutating batch job with a license requirement and git side effects, the definition is nearly complete, and an output schema exists so return-format detail is not needed. The remaining gap is failure/timeout semantics: what state entries are left in if the batch exceeds timeout_seconds, and whether a license-seat failure aborts the whole run.

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's Args block is the only documentation, and it compensates well: ids is described as the entries to check with the non-obvious default of every entry that has a script, and timeout_seconds as a limit on the whole batch rather than per entry. Minor gap: no guidance on id format or what happens to entries cut off by the timeout.

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+resource ('Re-run the verification scripts of experience entries') and enumerates the two triggering situations (post-upgrade, pre-approval draft). It is clearly distinguishable from adjacent siblings like diana_experience_review or diana_experience_add, which implies human review and creation rather than script re-execution.

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?

It gives explicit when-to-use conditions: 'after an upgrade, or to confirm a draft before proposing it for approval'. What it lacks is an exclusion or explicit alternative — e.g. when to run diana_experience_review instead — so the agent must infer the boundary.

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