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). The description adds useful behavior beyond that: the result includes the input face itself and neighbors, and neighbors are sorted by area descending, which is not in the schema or 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 sentences, front-loaded with the return contents and sorted order, followed by the intended use. No filler, though the field enumeration makes the first sentence dense.

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 read-only, three-param inspection tool with no output schema, the description covers return contents, sort order, and intended use. It is nearly complete; only the absence of explicit ordering rationale or edge-case behavior (e.g., boundary faces with no neighbors) 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?

Schema coverage is 100%, so all three parameters (body, index, document) are already described, and the description adds no syntax or format detail beyond what the schema provides. The organic connection to smallest_faces in the schema description is echoed here but adds little new. Baseline 3 is appropriate when the schema does the heavy lifting.

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: returns the given face plus every edge-adjacent face, with an explicit field list (index, area mm^2, edge count, surface type, center point mm). This is far more than a name restatement and an agent can identify the operation's scope immediately.

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 a clear use case: 'Use it to see what a suspicious small face sits between before excluding or fixing it,' which ties it to smallest_faces via the index param. It stops short of naming explicit when-not-to-use conditions or a true alternative sibling, so it's 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=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds meaningful scope detail (mm units, which feature attributes are returned, the Unwrap count) but no behavioral traits beyond that, since output_schema is absent and return shape is only described in prose.

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, no filler, and the summary content is front-loaded before the usage instruction. Every clause contributes either scope or routing 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?

With no output schema present, the description carries the full burden of describing the return payload, and it does so thoroughly — body properties, units, feature tree fields, and feature counts. An agent knows exactly what it will receive before calling.

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 optional parameter, so the schema already explains that omitting 'document' falls back to the active document. The description adds nothing about the parameter, which is acceptable at this baseline.

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 gives a specific verb (summarizes) and resource (a part document) and enumerates the exact payload: per-body solidity, face/edge/vertex counts, bounding box in mm, the feature tree with suppression state, and Unwrap feature count. It implicitly separates itself from the face-level siblings by positioning itself as an orientation step, though it never names smallest_faces or face_neighbors directly.

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 states the usage context clearly: 'Use it to orient yourself in a model before inspecting individual faces,' which routes the agent to this tool as a first pass. It stops short of stating when not to use it or naming the alternative inspection tools explicitly.

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 destructiveHint=true, non-idempotent and non-read-only, so the safety profile is covered. The description adds real context beyond that: full access under the user's permissions, the ability to modify/close documents, and a hard output contract (exactly one line of JSON) with a worked example.

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 the purpose, then the helper vocabulary, then the output contract, then routing guidance — a logical order with no filler. It is dense because the escape hatch carries a lot of essential contract, but each 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?

For a high-risk, no-output-schema tool this is complete: it covers execution scope, permissions, destructive potential, the predefined environment, the strict JSON output requirement, and when to avoid it. An agent has everything needed to call it correctly or decide not to.

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 the baseline is 3 for both parameters. The description goes further on the `script` param by documenting the predefined helpers ($inv, $MISSING, Get-Doc, FaceInfo) and the required JSON output shape — meaningful semantics the schema does not carry. The `timeout` param is left to 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+resource ('runs arbitrary PowerShell with full access to Inventor's COM API') and frames itself precisely as an escape hatch relative to the other tools. An agent immediately knows this is the general-purpose fallback, distinct from the narrow siblings like smallest_faces or face_neighbors.

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 gives the when-to-use condition ('anything the other tools don't cover') and the when-not ('Prefer the dedicated tools when they fit'), plus a risk caveat that it can modify or close documents. It does not name which specific siblings apply to which case, but the routing rule is clear.

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/non-destructive/closed-world, so the safety profile is covered. The description adds ordering guarantees (area ascending) and the exact return payload, which matters because no output schema exists. It does not mention cost, limits, or behavior on bodies with fewer than N faces.

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, no filler, and the core behavior (what is listed, in what order, with what fields) is front-loaded before the use case. 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?

With no output schema, the description fully compensates by enumerating the returned fields (index, area in mm^2, edge count, surface type, center) and the aggregate totals. Combined with complete schema coverage, nothing needed to call or interpret the 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?

Schema description coverage is 100%, so 'body', 'count' and 'document' are already documented in the schema. The description only restates 'N smallest faces' and never mentions the document parameter or the 1-based body indexing, so it adds little beyond the structured fields — 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 ('Lists the N smallest faces of a body') plus the sort order, and the return-field enumeration makes the operation unambiguous. An agent can distinguish it from siblings like face_neighbors or model_info 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 motivating scenario (finding sliver or near-zero-area import defects from STEP/IGES) and points to the downstream tools the returned indices feed into. It stops short of saying when not to use it or what alternative to prefer for other diagnostic needs, so it is clear context rather than 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the COM transport dependency and the exact return payload (version, active document, all open documents with path, type and unsaved flag), which tells the agent this call can fail if Inventor is not running.

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, and the purpose plus the invocation instruction ('Call this first') are front-loaded before the return-value detail. Every sentence carries information the 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?

With no output schema, the description carries the burden of describing return values and does so fully. For a zero-parameter status/discovery tool with rich annotations, nothing an agent needs to call it 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?

The tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. The description instead usefully frames the output as the source of identifiers for other tools.

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 ('Checks that Autodesk Inventor is running and reachable over COM') and then enumerates exactly what it returns. It is unmistakably distinct from the sibling tools (model_info, smallest_faces, face_neighbors, unwrap_try, script), which are all geometry/scripting operations rather than session discovery.

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 states when to use it: 'Call this first to get the document names the other tools accept,' which establishes ordering relative to the siblings. It does not name a specific alternative or state a when-not condition, but for a prerequisite/discovery tool that is a minor omission.

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 declare readOnlyHint=false and destructiveHint=false, which alone would be ambiguous for a feature-creating tool. The description resolves this by explaining that the created feature is deleted immediately by default, leaving the document unchanged, and that keep=true modifies the model. It also discloses the returned diagnostics (error, last error message, time, face count, area, bounding box), which the annotations do not.

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 the core action and outcome, then the side-effect semantics, then the motivating use case. Dense but every clause carries information; 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?

With no output schema, the description compensates by enumerating what is reported on success and failure. Combined with the 100%-covered input schema and the keep semantics, an agent has everything needed to call it correctly and interpret 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 every parameter is already documented in the schema. The description adds meaning only for keep, which the schema already explains, and says nothing about body, alignment, auto_face_chain, or merge_result_body beyond what the schema provides.

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: attempts Inventor's Unwrap on a face set and reports the outcome. This is clearly distinguishable from siblings like status, model_info, smallest_faces, and face_neighbors, which supply indices rather than perform the operation.

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 a clear use case ('find which face set unwraps, which the Inventor UI does not tell you') and explains the default vs keep=true behavior. It does not name alternative tools or explicitly state when not to use it, but the context is sufficient to select it.

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