Record Automation Run

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

Beyond the annotations (mutation, non-idempotent, non-destructive), the description discloses real side effects: the run appears under Recent runs, updates the card's last-ran timestamp, and can surface the proposed jobs in the Agent inbox. It also states the 200-row retention cap, which annotations do not convey. Non-destructiveHint plus silent eviction of older runs is a mild tension, but it is a documented cap rather than a contradiction.

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?

Front-loads the core action, then spends a long clause enumerating UI surfaces (Recent runs, card timestamps, Agent inbox) that is informative but slightly sprawling. Nothing is off-topic and every sentence earns its place, though the middle sentence could be tighter.

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 3-param write tool with no output schema, it covers the essentials: what is stored, side effects, retention, and the return ("Returns the stored run"). The report-shape details live in the schema, so the description need not repeat them; only the retention boundary and idempotency of repeated identical runs go unaddressed.

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 only 33%, and the description fills the biggest hole by naming the valid card ids (mail-status, job-hunt, referral-pages, tailor-run, apply-session) and the 40-character custom-name rule for `automation`. It also expands the `outcome` enum into plain meanings (ok / partial = some work failed / failed = none done), which the bare enum does not.

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?

Opens with a specific verb+resource: "Stores one finished automation run." It immediately distinguishes this from sibling recorders (record_triage, record_decision, report_failure) by tying it to automation runs and describing where the stored run surfaces. An agent can tell what it does without opening the schema.

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 "finished automation run" scoping plus the list of valid automation card ids gives clear context for when to call it, and the 200-run retention implies it is an append-style ledger. It does not, however, name an alternative or state any exclusion, so it stops short of an explicit when/when-not rule.

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