CloudCrane workspace

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds the notable behavioral fact that this returns a single fully-hydrated dataset (columns, types, identity column, origin) rather than a summary, but it does not address auth, error behavior, or how an unknown id is handled.

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?

A single compact sentence with no filler, front-loading the resource and immediately following with the returned fields. It earns its place, though it could be marginally 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?

With an output schema present, the description needn't spell out return values, and annotations carry the safety profile, so the terse description is nearly sufficient. Combined with the id provenance reference, an agent has what it needs to invoke correctly.

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 sole parameter is documented as the dataset id 'from list_datasets.' The description repeats that provenance rather than adding syntax, format, or constraint detail beyond the schema, so 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 (fetch one dataset by id) and enumerates what comes back (columns, types, identity column, origin). It names list_datasets as the source of the id, implicitly distinguishing itself from that sibling. Phrasing is slightly clipped but the 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?

The reference to 'the id list_datasets gave' implies the call follows a list_datasets lookup, which is useful sequencing context. However, there is no explicit statement of when to use this instead of siblings like get_run or list_datasets, and no exclusions or prerequisites.

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?

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds substantive content-level context about what the report aggregates — withheld/generated records, locked values, open review items by reason, missing safety fields, blockers in plain words.

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?

A single front-loaded sentence with no filler; the list of report contents is dense but each item earns its place. Slightly long but structurally sound.

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 read tool with an output schema and full annotation coverage, the description is complete enough: it explains the report's scope and contents without needing to restate return values. Only the when-to-use guidance is absent.

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?

With a single parameter and 100% schema description coverage ('The dataset's id, from list_datasets'), the schema already carries the meaning. The description adds no additional guidance about the dataset_id, so the baseline of 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?

The description states a specific resource (dataset readiness toward a release) and enumerates what the report surfaces, which distinguishes it from siblings like get_dataset and get_receipts. It is clear but framed as a question about the dataset rather than an explicit verb+resource statement.

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 phrase 'what stands between a dataset and a release' implies a pre-release gating use case, but the description never states when to call this instead of get_dataset or list_review_items, nor any preconditions. Usage is only inferable.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful content context about what a 'receipt' contains, but says nothing about volume, pagination, or authorization scope beyond the annotations.

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 with the content payload front-loaded and no filler; the second sentence handles the id-source prerequisite efficiently. Slightly dense phrasing 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?

With an output schema present, the description needn't enumerate return values, and annotations plus a fully-covered input schema remove the usual gaps. It is nearly complete for this read-only lookup, missing only contrast with sibling tools.

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, including that `field` maps to outputField from list_contracts. The description's note that record ids come from list_review_items merely corroborates the schema rather than adding new semantics.

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 states the resource precisely: per-value decision receipts for one record, itemizing rule/model origin, confidence, contract version, and approver. That is far more specific than the name get_receipts alone, though it never explicitly contrasts itself with siblings like get_readiness or get_dataset.

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 tells the agent where the required input comes from ('Record ids come from list_review_items'), which is a genuine prerequisite hint, but it gives no when-to-use vs when-not guidance and names no alternative for a different question shape.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context: the full status lifecycle (queued/running/succeeded/failed/cancelled), the progress and settlement counters, and that failure reasons are returned. It does not cover error or auth behavior, but it goes meaningfully beyond the annotations.

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?

A single front-loaded sentence that names the resource first and then spends the rest on what the caller gets back. No filler sentences and nothing repeated.

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 read tool with full schema coverage, complete annotations, and an output schema, the description supplies everything needed to call it and set expectations. The id's origin, the status vocabulary, and the failure case are all present.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents run_id fully. The description restates its provenance ('start_run gives it') but adds no format or constraint detail beyond the schema, making the baseline 3 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+resource ('One run by id') and immediately scopes it with the origin of the id ('start_run gives it'). The enumerated status values and counters make it unmistakably distinct from siblings like get_dataset and get_receipts.

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 tells the agent where the run_id comes from (start_run), which is useful context, but never states when to call this versus get_receipts or list_review_items, nor any exclusions. Usage is implied rather than guided.

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?

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the safety profile is handled. The description adds substantive domain context beyond that: the meaning of a safety field's 'ratchet' policy (values can be added but never quietly removed), confidence thresholds, versions, and that this is the customer-asserted vocabulary. That is real behavioral/semantic color, though it does not discuss auth or pagination.

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 resource statement is front-loaded, which is good, but the body is one long run-on sentence enumerating field-by-field contents that the output schema already exposes. Dense and somewhat redundant rather than wasteful, so mid-range.

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 annotations covering safety and an output schema present, return values need not be spelled out — yet the description spends most of its length enumerating those returns, duplicating structured data. It does add the useful 'read before reasoning' cue, so it is adequate but not efficient for a simple one-parameter read 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 description coverage is 100% and the single parameter dataset_id is fully documented in the schema (including the pointer to list_datasets). The description adds nothing about the parameter, 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?

The description clearly identifies the resource ('the contracts on a dataset') and enumerates what each contract contains, giving an agent a concrete picture of the payload. It does not, however, differentiate this tool from the similarly named sibling list_value_sets, so an agent must infer the boundary. A clear purpose with a sibling-differentiation gap lands at 4.

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 an explicit directive — 'read it before reasoning about any field value' — which tells the agent when this tool is the right call. It stops short of naming alternatives or stating when not to use it (e.g. versus get_dataset or list_value_sets), so it is clear context without exclusions.

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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description adds the composition of each record (columns, contract fields, origin, record count), which is useful orientation, but says nothing about ordering, pagination, or volume 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?

Two sentences, front-loaded with the scope and closed with the routing cue. Every clause carries information; nothing is 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?

With no parameters, full annotation coverage, and an output schema that carries the return shape, the description is nearly complete. Only minor gaps remain around ordering/pagination of the list, which the output schema does not address.

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; the 4 baseline for a no-parameter tool applies. Schema coverage is also 100%.

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 (listing every dataset in the workspace) and enumerates the returned scope: columns from imported data, contract-added fields, provenance, and record count. The plural 'every dataset' plus the 'Start here' cue separates it cleanly from the singular get_dataset sibling.

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?

'Start here' gives a clear orientation context for when to reach for this tool first, and it is obviously the enumeration counterpart to get_dataset. It stops short of explicit when-not-to-use guidance or naming a sibling alternative.

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?

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered. The description adds real behavioral context beyond them: the result ordering, that these are run-produced unresolved values, and that resolution is a human act logged to a receipt. It doesn't describe pagination or the return shape, but an output schema exists.

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 with the ordering front-loaded and the human-decision constraint following. Dense and purposeful, though the compressed phrasing costs a little immediate readability.

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 an output schema present, return values need not be explained, and annotations carry the safety profile. Ordering, scope (all datasets unless filtered) and the human-resolution boundary are covered, leaving only minor gaps like result size behavior.

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% — limit, dataset_id and include_record are each documented in the schema, including the record-data permission caveat. The description adds no parameter-level meaning, so the baseline of 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?

Names a specific resource (unsettled values awaiting human review) and its triage ordering — ratchet blocks, then abstentions, then sub-threshold answers. This is far more specific than 'list review items' and clearly separates it from siblings like list_contracts or get_receipts.

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?

States the decisive usage constraint: resolving an item is a person's decision, not an agent's, and a receipt records who decided. That tells the agent this is a read/triage surface, not an action surface. It stops short of naming which sibling to call for adjacent needs.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is fully covered. The description adds useful shape information—each set carries a current version and entry count—but does not go beyond that (no pagination, ordering, or size 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?

Two compact sentences with the resource front-loaded and the definitional gloss immediately after; nothing is padded. The second fragment ('Each with its current version and entry count') is information-dense rather than wasteful.

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 zero parameters, full annotation coverage, and an output schema that documents the returned fields, the description only needs to convey what the tool returns at a high level, which it does. Only the omission of any usage routing keeps it from a 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly adds no parameter detail because there is nothing to parameterize.

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 identifies a specific resource (value sets in this workspace) and explains what they are (versioned lists of entries a field picks from), so an agent can tell it apart from list_contracts/list_datasets by domain. It never states the verb 'list' explicitly, relying on the name and the plural subject to imply enumeration, so it falls just short of a clean 5.

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 alternatives such as list_datasets or get_dataset, and no prerequisites or exclusions. The conceptual definition of a value set implicitly hints at the use case, but no actionable guidance is given.

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