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 exactly which tasks are mutated (queued/scheduled), which are left untouched (running/completed/failed/cancelled), and the return shape (count cancelled). It omits auth requirements and whether cancellation is reversible, which are meaningful gaps for a destructive bulk operation.

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 short sentences, front-loaded with the destructive scope, followed by exclusions and return value. Nothing is redundant or padded.

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 output schema, the description correctly supplies the return value (number cancelled) and fully characterizes the effect and boundaries of the operation for a single-parameter tool.

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% and the enum already documents the valid status values, so the description's 'Optionally filter by status' adds no syntax or behavior beyond the schema. Baseline 3 is appropriate.

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 (bulk-cancel), an explicit resource (every task in the queue), and a precise scope (only still-cancellable statuses). This clearly separates it from the single-task sibling cancel_task.

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 word 'Bulk' plus 'every task in the queue' makes the bulk-vs-single context clear relative to cancel_task, and the eligible/untouched status lists frame when it applies. It stops short of explicitly naming an alternative or stating when not to use it.

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 does well: it discloses idempotency, the no-error behavior for completed/failed/cancelled tasks, and the sole failure mode (unknown task_id). It omits permission/auth requirements and whether cancellation is reversible.

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 tight sentences, front-loaded with the action and its scope, followed by the exact error semantics. No filler.

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 one-parameter mutation with no annotations or output schema, the description covers the key agent concerns: eligible task states, idempotent return behavior, and the lone exception case. What it lacks is auth/permission context and any note on cancelling in-flight tasks.

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% and the single parameter is fully documented in the schema. The description adds no meaning about task_id format or source beyond what the schema provides, so the baseline 3 applies.

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+resource (cancel a task) and narrows the eligible state to 'queued or scheduled'. It implies a single-task scope that separates it from cancel_all, but never names the sibling 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?

The error/idempotency conditions give usable context, but there is no explicit when-to-use versus siblings like cancel_all, retry_task, or expedite_task. The single-task scope is only inferred from the wording.

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 behavioral burden and does so partly: it declares the operation read-only, discloses that the queue persists across host restarts, and describes what a detail response contains (carbon receipt with estimated vs. actual grams, grid_source, energy_source). It does not discuss permissions, rate limits, or output volume, but covers the important traits.

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 front-loaded sentences with no filler; the no-argument case is stated first, then the task_id case, then the safety tag. Every clause carries information an agent needs.

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?

There is no output schema or annotation block, so the description must explain returns, and it does reasonably well by naming the summary scope and the carbon-receipt fields. It is close to complete for a one-parameter read tool, lacking only auth/permission context.

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%, and the task_id property already documents the summary-vs-detail switch, so the baseline is 3. The description enriches this slightly by naming the extra fields returned for a single task, but adds no syntax, format, or constraint information 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?

States a specific verb and resource ('Report on the ebb-ai task queue') and clearly separates the two modes of operation (summary vs. single-task detail). No sibling tool reports on queue state, so it is easily distinguished from get_grid_forecast, schedule_task, or cancel_task.

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 explains both call shapes but frames them as parameter behavior rather than as a decision rule. It never states when an agent should check queue status versus using siblings like retry_task or cancel_task, so usage is only implied.

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 at all, the description carries the full behavioral burden and does well: it discloses the side effect on the resulting receipt (intensitySource='expedited'), the fact that a scheduled carbon optimization is overridden, and the precise rejection conditions. It does not cover auth requirements, idempotency of repeat calls, or rate limits.

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, zero filler, front-loaded with the action and its key consequence (carbon-window bypass) before the eligibility rules. Every sentence earns its place.

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 outcomes; it names the receipt field and the error behavior, which covers most of what an agent needs. Minor gaps remain around reversibility and permissions for an operation that intentionally overrides a carbon-optimized schedule.

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 baseline is 3, but the description adds real meaning by constraining which task_id values are legal (only queued/scheduled provider-call tasks), which the schema cannot express.

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 (dispatch/expedite), resource (queued or scheduled provider-call task), and the distinguishing behavior (bypassing the scheduler's carbon window). An agent can separate this from schedule_task, cancel_task, and retry_task purely from the description.

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 enumerates the eligible states (queued/scheduled provider-call tasks) and the rejected states (running, submitted awaiting Batch results, terminal completed/failed/cancelled), with the consequence of misuse (explanatory error). It does not route the agent to a sibling alternative, so it falls short of a full 5.

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 burden and does well: it declares 'Read-only; does not touch the task queue', which tells the agent this has no side effects on scheduled work. It also discloses the return semantics (g CO2e/kWh plus categorical bands), which is behavioral context beyond a typical read. It omits any note on forecast accuracy degradation or rate limits, keeping 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?

Three tight sentences, front-loaded with what the tool returns before the usage guidance and the safety note. Every clause earns its place; nothing is redundant with the name or title.

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 tool with no output schema, the description usefully explains return values (units and the five-band categorical scale) and the read-only guarantee. Coverage of the parameters is delegated to a complete schema, which is appropriate. Minor gaps (no note on pagination/horizon defaults beyond the schema, no failure modes for unknown region codes) keep it just below 5.

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 (region codes, hours 1-72 with default 24) are already fully documented in the schema. The description reinforces intent with 'for a region' and 'hour by hour' but adds no syntax, format, or edge-case detail beyond what the schema supplies, so the baseline 3 applies.

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 ('Return the projected electricity-grid carbon intensity') plus the granularity ('hour by hour') and scoping unit ('for a region'). An agent can distinguish this from siblings like recommend_window or check_queue_status without opening any 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?

Explicitly names the decision context: 'Use this when deciding whether to run an expensive AI task now or defer it.' That is a clear when-to-use signal. It stops short of naming the sibling alternative (recommend_window) or stating when-not to use it, so it is clear context without full routing guidance.

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 well: it declares "Read-only; does not touch the task queue," enumerates the returned fields (window, alternatives, batch_eligible, grid_source, reasoning), and warns that grid_source='mock' means synthetic data. It stops short of other operational context such as rate limits, auth requirements, or failure modes outside the carbon cap.

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 purpose, then usage, then returns, then safety posture in a tight sequence. Every clause carries distinct information (differentiation, return shape, mock-data caveat, read-only guarantee) with no padding.

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-parameter tool with nested objects and no output schema, the description compensates by enumerating the return payload. It does not fully cover the routing/candidate behavior, but that is documented in the schema, so the description is adequate though not exhaustive.

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 the schema already documents all six parameters in detail, including the routing semantics and defaults. The description adds no additional parameter-level meaning (e.g. syntax or edge cases for candidates/route_weights) beyond what the schema states, so the baseline 3 applies.

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+resource ("Return the optimal carbon-aware execution window for a task") and immediately delimits scope with "WITHOUT scheduling it." This directly contrasts with the sibling schedule_task, so an agent can distinguish commit-vs-preview 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?

Explicitly names the use case ("non-committal planning") and the decision it feeds ("before deciding whether to commit via schedule_task"), routing the agent to the correct sibling. The when-to-use condition is stated rather than inferred.

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 are provided, so the description carries the full behavioral burden, and it does well: it discloses the validity gate, the rejection error for wrong states, and the mutation side effect ('the new run's receipt overwrites the old'). It omits permission/auth requirements, which keeps it short of 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?

Three tight sentences: the action first, then the validity gate, then the side effect. Every clause earns its place, and the most important constraint is front-loaded after the verb.

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 one-parameter mutation tool with no annotations and no output schema, the description covers validity, error behavior, and the overwrite side effect. Return values need not be explained since no output schema exists; only auth/permission context 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 description coverage is 100% and there is a single parameter, so the schema already fully documents task_id. The description's reference to the failed task adds consistency but no meaning beyond the schema; baseline 3 applies.

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 ('Re-dispatch') and resource ('a failed provider-call task'), scoping it to provider-call tasks so an agent can distinguish it from siblings like schedule_task or expedite_task. Purpose is unambiguous.

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 names the precondition (status must be 'failed') and enumerates the rejected statuses (queued/scheduled/running/submitted/completed) with the resulting error. It stops short of naming an alternative tool for non-failed tasks, so it is strong guidance without full routing.

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 mostly does: it discloses off-peak dispatch, Batch API auto-routing with up to 50% cost reduction, grid-region/carbon-aware window selection, deadline conversion, and that a task_id is returned for later status checks. It stops short of stating failure semantics (e.g. what happens when no window meets a carbon cap or the deadline passes) and leans on promotional framing for what are really behavioral claims.

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 is front-loaded in sentence one and the routing/return facts follow in a logical order. The four-item 'parallel wins' block is longer than necessary and partly promotional, but the trigger-phrase enumeration and exclusions carry real selection value, so the length is mostly earned.

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 12-parameter, deeply nested tool with no annotations and no output schema, the description supplies everything an agent needs to decide to call it and how to shape the core call: purpose, triggers, exclusions, deadline/prompt mapping, provider/batch behavior, and the downstream status-check path. Remaining specifics (weights, output_path, redaction) are thoroughly covered by the 100%-covered schema.

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 the baseline is 3, but the description adds genuine mapping guidance beyond the schema: convert the user's deferral wording into an ISO-8601 deadline and pass the underlying request as the prompt. It does not, however, explain the relationship between candidate routing, weights, or the carbon budget beyond what the schema already says.

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 first sentence states a specific verb and resource with scope: 'Queue an AI task to run during off-peak hours inside the given deadline.' It also names the follow-up sibling (check_queue_status) and scopes itself apart from live/interactive work, so an agent can distinguish it from recommend_window or get_grid_forecast.

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 invocation triggers ('do this later', 'by tomorrow', 'overnight', 'no rush', etc.), concrete good-fit workloads (nightly digests, batch summaries, research sweeps), and explicit exclusions (live chat, interactive code edits, tasks the user is actively waiting on). This is about as complete a when/when-not statement as a description can carry.

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 does well: it discloses the scheduling side effect (window re-pick), the re-score behavior, and three failure modes (running/terminal state, invalid deadline, past deadline). It omits permissions/auth and idempotency, but the mutation and error profile is well covered.

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?

Effectively one sentence front-loading the action and effect, with the error conditions tagged on efficiently. No filler and nothing that restates the name or title.

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 and no annotations, so the description must convey behavior; it covers the mutation, the rescheduling semantics, and failure cases adequately. The one real gap is what the tool returns (new window, new score, or a status) for a caller needing to confirm the result.

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 by the schema, which is the baseline 3. The description reinforces that the deadline must be future-dated, consistent with the schema's note, but adds no format or syntax detail beyond it.

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 compound verb (re-score and reschedule) plus the resource (queued or scheduled task) and the mechanism (scheduler re-picks the cleanest window inside the new deadline). It is clearly distinguishable from siblings like schedule_task or retry_task, though it never names an alternative.

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?

Applicability is defined by state: only queued or scheduled tasks qualify, and running/terminal tasks are excluded via the throw condition. The 'when not to use' is implied through those error cases rather than stated as an explicit routing rule to a sibling.

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