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

With no annotations present, the description carries the full burden. "Inspect" and "summaries" correctly signal a non-mutating, read-only operation and pre-declare the returned fields (id/name/niceName/type), but nothing is said about permissions, cost, or behavior when nothing is selected or no composition is active.

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 sentence, front-loaded with the verb and the returned payload, with the scope qualifier at the end. No filler and nothing that could be cut.

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-optional-param read tool with no output schema, the description names the exact fields returned and the two scopes it can inspect, which is enough to call it correctly. Only the empty-selection/no-active-composition edge case is unaddressed.

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%, but the single parameter is an enum whose two values are explicitly mapped by the phrase "selection or active composition roots," so an agent can choose the default or override with intent. The description effectively compensates for the undocumented 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 (Inspect) and resource (compact layer id/name/niceName/type summaries) plus the scope it operates on (selection or active composition roots). It implicitly separates itself from cavalry_run_script and cavalry_run_preset, which execute things rather than read layer metadata, though it never names 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?

"for the selection or active composition roots" implies the situations where the tool is relevant, but there is no explicit when/when-not guidance and no direct routing to or away from cavalry_run_script and cavalry_run_preset. Usage has to be inferred from the scope phrase.

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. It usefully says the build happens in one atomic execution, but it does not disclose mutation side effects, required Cavalry state, failure behavior, idempotency, or what is returned after the rig is built.

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 front-loaded sentence with no wasted words. It is appropriately concise, though the extreme terseness contributes to the missing usage and parameter details elsewhere.

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?

This is a complex mutation tool with a large enum, a free-form nested params object, no annotations, and no output schema. One sentence stating that it builds a parameterized rig is not enough to tell an agent how to invoke it correctly or what to expect from the atomic execution.

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 says the rig is 'parameterized'. It does not explain the 118-value name enum, what the free-form params object can contain, how params override preset defaults, or whether any params are required beyond name.

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 and resource: 'Build a parameterized procedural motion rig' in 'one atomic Cavalry execution'. It is clear what the tool does and implies preset-driven rig creation, but it does not explicitly differentiate itself from cavalry_run_script or cavalry_inspect.

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 when-to-use guidance, no exclusions, and no mention of the sibling tools cavalry_run_script or cavalry_inspect. The agent is left to infer that this tool should be chosen when a named preset is desired rather than a custom script.

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 two real traits: all effects collapse into one Undo group (atomicity), and a returned value is read back as JSON (serialization requirement). It says nothing about permissions, error/failure behavior, whether the script can leave partial state on failure, or what _mg helpers actually are.

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 sentences, front-loaded with the operation and followed by the two constraints that matter. No filler, though the phrasing is terse enough to be slightly cryptic.

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 scripting tool with no annotations or output schema, the description covers the return path ('JSON readback') and undo semantics, which is more than most. Gaps remain around the _mg helper surface and failure behavior, which matter for arbitrary code execution.

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 single `code` parameter has 0% schema description coverage, so the description must compensate. It does add guidance — the code may use _mg helpers and should return a JSON-serializable value — but does not clarify the string format, expected structure, or any length/context constraints.

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: run batched Cavalry JavaScript. Adds the distinguishing traits (with _mg helpers, a single Undo group), which separates it from a plain script runner. It does not explicitly contrast with cavalry_inspect or cavalry_run_preset, so sibling differentiation is only implicit.

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?

No statement of when to use this rather than cavalry_run_preset or cavalry_inspect, and no prerequisites or exclusions. 'Batched' hints that this suits multiple operations, but the agent must infer that from a single adjective.

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