Sandbox Timer

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the API key materially changes scope, and plan tier caps the window (Free 7 days, Pro 30). It omits whether the operation is strictly read-only and how the key is actually supplied, which are the remaining gaps.

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?

Very compact and front-loaded: the output scope comes first, then the key/fleet behavior, then the tier limits. The telegraphic phrasing ('from what track_sessions has seen') is slightly awkward but every clause carries information.

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, no-output-schema, no-annotation tool, the description covers the output content, the data source, auth-driven scoping, and tier limits. The one actionable omission is how an API key is presented to the call, since no parameter exists for it.

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 100%, so both parameters are already documented, making 3 the baseline. The description adds a little meaning by tying fleet scoping to key presence and restating the tier-based day cap, but offers no syntax or format detail beyond the schema.

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 names a specific output — which sandboxes were flagged idle and the idle time cost, broken down per provider — and ties the data source to track_sessions. It is clearly distinct from set_idle_rules (configuration) and weekly_report (time-based digest), though it doesn't explicitly contrast itself with those siblings.

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 real conditional guidance for the fleet parameter: omit it without an API key, and the call spans every fleet on that key. But there is no guidance on when to choose this over weekly_report or usage_and_upgrade, and no stated prerequisites beyond the key behavior.

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

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: persistence on Pro versus a non-mutating preview on Free, plus the fallback pattern for Free users. However, it never says whether it replaces or merges with existing fleet rules, what omitted optional fields do given zero required parameters, or anything about permissions/quota for the Pro write.

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 dense sentences with the core action and field list front-loaded, and the Free-tier caveat correctly placed last. The parenthetical alternative is slightly compressed but earns its space since it prevents a wrong call pattern.

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 5-parameter, all-optional mutation tool with no annotations and no output schema, the description covers purpose, fields, and tier behavior, which is a reasonable baseline. It still omits the update semantics (replace vs merge) that an agent needs before calling with a partial payload.

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 20% (only 'fleet' is documented), so the description has to compensate. It does add real semantics for two parameters ('idle_minutes threshold', 'default rates_per_hour by provider') but leaves max_lifetime_minutes and alert_webhook as bare names with no units, format, or expected values, so the gap is only partially closed.

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?

States a specific verb and resource ('save the rules ... to a fleet') and enumerates exactly what is persisted: idle_minutes, max_lifetime_minutes, rates_per_hour, and alert_webhook. It also explicitly positions the tool relative to the sibling track_sessions, which is the tool that applies these rules, so the agent can tell them apart without opening either 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?

Gives clear tier-conditioned guidance: on Pro it persists the rules, on Free it 'returns a preview ... and saves nothing', with the explicit alternative of passing the same values on each track_sessions call. It lacks an explicit statement of when rules must be set at all (or what happens when a fleet already has rules), so it stops short of full when/when-not coverage.

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

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

With no annotations, the description carries the full burden and delivers: it discloses the Free watch-only vs Pro act distinction, that Pro POSTs one webhook alert per sandbox, and that it never holds provider keys or kills anything itself. This is exactly the behavioral context an agent needs before invoking a mutating-by-proxy tool.

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 core action and cadence are front-loaded, and the dense prose is justified by a genuinely complex tool. It is information-rich rather than padded, though the second half packs several distinct behaviors into long clauses.

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?

No output schema exists, so the description must explain returns — and it does, describing idle detection, dollar costs, and ready-to-run kill calls, plus the Pro/Free behavioral split and the key-security caveat. Nothing an agent needs to call this 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 high (83%), so the schema already documents the parameters in depth, and per the rubric the baseline is 3. The description only loosely echoes parameters ('your threshold', 'hourly rates you pass') without adding syntax or semantics beyond what the schema states.

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?

States a concrete verb and resource: send running sandbox sessions and receive back idle/over-lifetime sessions, cost figures, and kill calls. The purpose is unmistakable, though it never names a sibling (idle_report, set_idle_rules, weekly_report) to sharpen the boundary.

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?

Explicitly tells the agent when to call it (on a heartbeat, e.g. every 5 minutes) and encodes the Pro-vs-Free decision logic. It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it sits below the top tier.

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

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

No annotations, so the description carries the burden. It adds useful context: free tier of 500 calls/day, not metered. However, it doesn't state whether the call itself counts toward quota, rate limits, or whether the upgrade link is static/dynamic.

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 short, front-loaded sentences with no waste. The primary output is stated first, followed by the supporting quota context.

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 no-param, no-output-schema read tool, the description covers what is returned (usage and upgrade link) and the quota context. It lacks detail on return format, but that's minor given the simplicity.

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?

Zero parameters, so baseline is 4. The description correctly indicates the scope is implicit (your key or IP), needing no input.

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?

States a specific verb ('Show') and resource ('today's usage for your key or IP') plus a secondary output (the upgrade link). It's clearly distinguishable from siblings like budget_status and weekly_report which deal with budgets/reports.

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?

Implied usage via 'today's usage' and the free-tier context, but no explicit when-to-use or when-not-to-use versus siblings like budget_status or weekly_report. The agent must infer that this is a quick self-check rather than a budget query.

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

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

With no annotations provided, the description carries the full burden and does notably well: it declares 'Read-only; sends nothing,' which establishes it is a safe, side-effect-free read, and flags the free API key requirement. It stops short of disclosing rate limits, whether the report is computed fresh or cached, or what a free-tier response looks like.

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?

One dense, front-loaded sentence naming the return contents, followed by two short behavioral clauses. Zero filler, and the most decision-relevant information (what you get, 7-day window) comes first.

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?

With no parameters, no annotations, and no output schema, the description does the work of all three: it describes the return payload field by field, states the safety profile, the auth requirement, and the tier behavior. Nothing essential to calling or interpreting this report 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description's enumeration of returned fields is a bonus that compensates for the absent output schema.

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?

States a specific verb (summary) and resource (last 7 days of sandbox idle data) and enumerates the exact content returned: sandboxes watched, idle count, dollar cost, kill calls. The 7-day window implicitly distinguishes it from idle_report, but no sibling is named, so the differentiation is left to inference.

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?

There is no statement of when to call this versus idle_report or usage_and_upgrade, and no exclusions. It notes 'Needs a free API key,' which is a prerequisite rather than usage guidance, and the tier note hints at Pro gating but never tells the agent when this report is the right choice.

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