CADProps

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

Annotations already declare it is non-read-only, idempotent, non-destructive, and closed-world, so the bar is lower. The description nevertheless adds real value: the download link expires in 30 minutes and the fidelity of STEP output depends on whether the source was read exactly, which is the key caveat an agent needs. It does not mention the async/running status behavior, but the schema's wait_seconds covers that.

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: purpose and return value first, then the fidelity caveat, then the mesh-format rule. Every sentence carries distinct information and nothing is redundant.

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 properly discloses the return value (download link, 30-minute expiry) and format trade-offs. The only gap is not describing the status=running polling outcome, which the schema only hints at via wait_seconds.

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 meaning beyond the schema by explaining what the solid-vs-triangulated STEP distinction actually implies for downstream editability in CAD software. That interpretive context is not in the enum description.

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 (convert), the resource (a file opened with inspect_cad), the three supported targets, and the return value (download link). It also implicitly distinguishes itself from inspect_cad by naming it as the prerequisite step.

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?

"Convert a file opened with inspect_cad" gives a clear prerequisite that selects this tool over its sibling. It does not state when not to use it or what to do with an upload_ticket flow (the schema covers the latter), so it stops short of 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 read-only, non-destructive and closed-world, so the safety profile is covered. The description goes beyond them usefully: one-hour file retention, and the important caveat that Creo .prt files with triangle strips yield a partial preview with unverified units and no physical measurements, while other Creo and CATIA .CATProduct files show only a thumbnail. That is exactly the kind of degraded-output disclosure an agent needs; it only lacks detail on status=running behavior, which is left to the schema.

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?

Purpose and behavior lead, with the caveats and upload flow before the format list. The 70+ entry format enumeration is bulky but genuinely useful for deciding whether a file is supported, so it earns its place, though it could be trimmed or grouped to reduce scan cost.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description still supplies the retention window, the upload-link fallback, and the per-format fidelity caveats that determine whether results are trustworthy. Minor gap: nothing about the asynchronous status=running outcome beyond what the wait_seconds schema field implies.

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 all four parameters (ref, file, wait_seconds, upload_ticket) are already documented, which sets the baseline at 3. The description adds only the framing that omitting a file triggers the upload-link flow; it does not explain ref reuse or the wait_seconds/running semantics beyond what the schema states.

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 ('Open a CAD file on CADProps servers') and enumerates exactly what it reports: format, size, volume, area, units, accuracy, plus an interactive 3D preview. That is far more than a restatement of the title and lets an agent distinguish it from convert_cad or open_in_workspace.

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 concrete routing guidance for the upload flow ('Call with no file to get a one-time upload link', files deleted about one hour after upload) and the schema reinforces 'prefer this when the host already uploaded the attachment'. It does not explicitly contrast against the sibling tools convert_cad or open_in_workspace, so it stops short of a 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 annotations declaring readOnlyHint=false and destructiveHint=false, the description supplies the crucial context the annotations omit: the link is one-time, expires in 15 minutes, and opening it disables the chat preview and links for that file. That side effect sits in tension with destructiveHint=false, but it describes invalidation of an access artifact rather than data destruction, so it reads as added disclosure rather than a contradiction.

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, with the return value and its expiry front-loaded and the irreversible side effect placed second where it lands hardest.

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-param tool with no output schema and no nested objects, the description covers the return value, its lifetime, and the consequence of use — the essentials an agent needs. It does not address what happens on a second call or whether the ref remains usable elsewhere, minor gaps 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 100% and the single 'ref' parameter is fully documented in the schema, including the explicit contrast that 'An upload_ticket is not a ref.' The description adds nothing about parameters, 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 verb and outcome — 'Return a one-time link ... that opens this file in the CADProps web workspace' — and scopes the resource to a single file. It is clearly distinct from inspect_cad/convert_cad/refresh_view_token in effect, though it never names a sibling to sharpen the contrast.

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?

Usage is only implied: 'for measuring, sectioning and sharing' hints at the intent, and the warning about previews/links stopping implies a point-of-no-return condition. There is no explicit when-to-use statement, no prerequisites, and no named 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 readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that the token being renewed is read-only, but says nothing about token lifetime, whether the old token is invalidated, or rate limits on renewal — notable gaps for a credential-issuing 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?

A single dense sentence with zero filler that front-loads the consumer and the action. Nothing could be removed without losing 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 one-parameter, fully documented, annotated tool with no output schema, the description covers what it does and who uses it. It could go further by explaining the renewal trigger and what a successful call returns, but the essentials are 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?

There is one parameter with 100% schema description coverage, and the schema explains it fully ("The ref from an inspect_cad result whose preview token should be renewed"). The description adds no parameter-level detail, which is acceptable but not value-adding, 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 names a specific verb (renew) and resource (read-only preview token) and identifies the consumer (CADProps preview), so an agent knows exactly what the tool does. Sibling tools (convert_cad, inspect_cad, open_in_workspace) are unrelated, so no explicit differentiation is needed, though none is offered.

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?

"Used by the CADProps preview" implies the tool is scoped to that internal workflow, which indirectly signals it isn't a general-purpose call. However, it never states when the token should be renewed (e.g., on expiry/401) or what to do instead, leaving the trigger condition to inference.

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