show_new_episodes

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

With no annotations provided, the description carries the full disclosure burden and exceeds it: it reveals the exact request profile ('M saved shows → M+1 requests'), flags the cost scaling as a WARNING, and names both mitigations (max_shows to budget, dry_run to preview cost). It also discloses the fetch path (/me/shows then per-show episode lookups). This is precisely the behavioral context an agent needs to call a fan-out scan responsibly.

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?

Three sentences, front-loaded with the core purpose before mechanism and warnings. Every sentence earns its place; the WARNING block is long but contains high-value cost information. Mild redundancy with schema text (days default, max_shows, dry_run) prevents a 5, but nothing is wasted.

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 6-param, no-output-schema reporting tool, the description covers purpose, window, mechanism, cost, and budget controls — the hard parts are all present. The main gap is that with no output schema, it never describes the result grouping/shape beyond 'reports episodes,' and it omits explicit read-only reassurance, though response_format and max_results partially cover output expectations.

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 the baseline is 3. The description adds marginal value beyond the schema by wiring max_shows and dry_run into the cost model (budget + preview cost before running) and by re-stating the 7-day default for days, which reinforces rather than repeats the param docs. It doesn't add format/syntax detail beyond schema, but the cost-framing boost is genuine.

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 pair ('Find new episodes across your saved podcast shows') and adds precise scope: lookback window (default 7 days) plus marking which episodes are already saved. The saved-shows + time-window + saved-status framing clearly distinguishes it from single-show siblings like get_show_latest_episode and list_show_episodes, and from generic search tools, even without naming them.

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 makes the invocation scenario explicit — scan saved shows for recent episodes within a window — giving clear context for when an agent should reach for it. It does not name alternatives or when-not-to-use conditions, and closely related siblings (get_newly_released_episodes, shows_release_calendar) are never referenced, but the scope statement is specific enough that an agent can infer the right selection.

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