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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds valuable context: the review is 'deterministically' composed, field reads are resolved against named canvases, and the agent must never invent a value not present in `resolved`. This is meaningful behavior disclosure 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?

The description is compact and front-loaded with the core operation. Each sentence earns its place: the operation, the use case, and the critical no-invention instruction. There is no redundancy or 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?

The output schema and annotations cover return shape and safety, and the description gives strong procedural guidance. However, the unexplained `step` parameter and undefined 'named canvases' leave enough ambiguity that an agent may not know the full valid invocation space.

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 0%, and the description never explicitly explains `step` or `skill_id`. It refers vaguely to 'named recipe' and 'steps', but does not clarify whether `step` selects a single step or whether omitting it runs all steps. This is a significant gap for confident invocation.

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 operation: 'compose an Atlas-level review by walking a named recipe's steps' and identifies the scope as cross-canvas/cross-altitude reviews. It differentiates itself from sibling tools like vedha_get_canvas or vedha_get_diagnosis with the example 'Monthly Business Review'.

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 explicitly says to use the tool for cross-canvas/cross-altitude reviews, giving a concrete example. It does not explicitly state when not to use it or name alternative sibling tools, so it stops short of full exclusionary 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety and repeatability. The description adds the session-scoping constraint ('result returned earlier in this session'), which is useful behavioral context, but it does not disclose additional traits beyond what annotations already convey.

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 contains all necessary information with no filler. Every word contributes to explaining the tool's scope and purpose.

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 simple one-parameter, read-only tool with an output schema present, the description is nearly complete. It explains the purpose, the session constraint, and implies the input. It does not mention failure modes or how to obtain result_id, but these are minor given the tool's 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?

Schema description coverage is 0%, so the description must compensate. It indirectly indicates that result_id refers to a result from earlier in the session, but it never explicitly says 'provide the result_id of that result'. The parameter's meaning is partly inferable but not fully documented.

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 action ('Explain') and a specific resource ('which canvases and route produced a result'). It clearly distinguishes this audit tool from siblings like vedha_get_canvas or vedha_get_diagnosis by focusing on result provenance within the session.

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 gives clear context for when to use the tool: when a result was returned earlier in this session and the agent needs to know its origin. It does not explicitly contrast with sibling alternatives, but the session-scoped result auditing is a distinct and well-specified use case.

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=true and idempotentHint=true, so the 'Read' verb aligns with those. The description adds behavioral context beyond annotations by calling the model 'bounded' and by disclosing that results can be narrowed to one dimension and value. No contradiction with annotations is present.

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 description is exactly two sentences with no wasted words. The primary action and resource are front-loaded, and the optionality is stated in one compact follow-up sentence. The parenthetical enumeration adds useful content without bloat.

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 simple read-only tool, the description covers the core behavior, the bounded scope, and optional filtering. The output schema and annotations handle return format and safety profile. The only notable gap is the unexplained required canvas_id parameter, but the schema enum provides allowed values, so overall completeness is adequate.

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 0%, so the description must compensate by explaining parameters. It mentions 'dimension' and 'value' in the optional narrowing clause, giving those some meaning. However, the required canvas_id parameter is never described or mapped to 'one workflow,' leaving a significant gap for the agent.

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 uses the specific verb 'Read' and identifies the resource as 'one workflow's bounded semantic model' with a concrete list of contents (goal, drivers, inputs, guardrails, funnel, entities, dimensions). This clearly distinguishes it from the sibling audit/diagnosis tools by the nature of the data returned. It doesn't explicitly name a sibling to differentiate, so it misses the top score.

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 implies usage when you need a workflow's semantic canvas model, and the optional narrowing clause hints at filtering behavior. However, there is no explicit statement about when to choose this tool over vedha_get_audit or vedha_get_diagnosis, nor any mention of exclusions or prerequisites. Guidance is only implicit.

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 read-only and idempotent behavior, and the description does not contradict them. It adds useful behavioral context beyond the annotations: the tool is thread-scoped, stays inside one canvas, and returns guardrails plus a dimension breakdown.

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 description is short and front-loaded, with the core behavior stated first and the alternative routing stated second. Minor redundancy exists between 'for one canvas', 'Thread-scoped: stays inside one canvas', and 'Never use it for cross-canvas questions', but the structure remains efficient.

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?

The description does a good job with when-to-use and scoping, and an output schema exists to cover return values. However, with 0% schema description coverage and three parameters, the lack of detail about the 'dimension' and optional 'value' parameters leaves a meaningful gap.

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 0%, so the description must compensate, but it only loosely references 'canvas' and 'dimension'. It does not explain the optional 'value' parameter, define what 'dimension' should be, or clarify how canvas_id relates to the guardrails and breakdown.

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 verb ('Return') and resource ('guardrails and a dimension breakdown for one canvas'), and ties it to a causal 'why' question. It also distinguishes itself from siblings by explicitly naming the cross-canvas tool, vedha_get_atlas_review.

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 clearly says when to use the tool: for a causal 'why' question within a single canvas. It also gives an explicit exclusion and alternative: never use it for cross-canvas questions, escalate to vedha_get_atlas_review instead.

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=true and idempotentHint=true, so the safety profile is covered. The description adds the behavioral nuance that this is a preliminary scoping call but does not describe pagination, result size, ordering, or any side effects. With strong annotations and an output schema present, a 3 is appropriate rather than lower.

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 description is a single, dense sentence that front-loads the verb and object, then immediately provides the key usage cue. Every word earns its place; there is no filler or repetition of schema/annotation 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 zero-parameter, read-only, idempotent tool with an output schema, the description is complete: it names the resource, indicates the return scope, and states when to invoke it. Nothing an agent needs to decide whether to call this tool 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 the description does not need to explain parameter meanings. The schema coverage is effectively 100% (empty schema fully documented), and the baseline for zero-parameter tools is 4. The description even adds semantic context about what the returned 'contexts' refer to.

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 uses a specific verb ('List') and resource ('altitudes, workflows, and flows of the DataOrbit operating model'), clarifying both the action and the object. It also slots the tool relative to its get_* siblings by framing this as the scope-map listing entry point, so an agent can distinguish it without inspecting other tools.

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 explicitly tells the agent when to call this tool: 'Call this first when scope is ambiguous.' This is clear, actionable context for a common decision point. It does not enumerate exclusions or explicitly name alternatives, so it falls short of a full when-to-use/when-not-to-use guide.

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