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

No annotations exist, so the description carries the full behavioral burden. It implies a non-destructive calculation ('calculate', 'recommend'), but never confirms it is read-only, whether it mutates anything, or what thresholds define the 8K/16K recommendation. An output schema is present, which reduces the need to describe return values.

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 sentence with the core operation front-loaded and the secondary recommendation clause attached. No filler or redundant restatement of the title.

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 three-parameter computation with full schema coverage and an output schema, the description covers the essential operation and its advisory output. The only gap is that the 8K/16K recommendation logic is stated without any hint of the DPI thresholds that drive it.

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%, with each parameter documented including a concrete 24x36 example, so the baseline is 3. The description adds only the framing that width/height represent a desired physical print size, which the schema already conveys.

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 computed quantity (DPI for a given physical print size) and an additional deliverable (a recommendation on whether to upscale to 8K or 16K). This lets an agent distinguish it from siblings like get_image_metadata or upscale_image, though it never names those siblings explicitly.

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: an agent can infer this is a pre-print feasibility check that would precede upscale_image. There is no explicit statement of when to call this versus getting image metadata, and no exclusions or prerequisites are given.

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 does useful work by disclosing that this fetches from remote mirrors (network access) and writes into a local models directory (a mutation of local state). It stops short of the traits that matter most for a downloader: idempotency/skip-if-present behavior, overwrite semantics, file size or latency expectations, and failure handling.

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 front-loaded sentence with zero filler; source, action and destination all land immediately. Nothing is wasted, though there is no structure beyond a single clause.

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 tool with a full schema and an output schema, the description covers the essential shape of the operation. It is only marginally complete, however, because an agent cannot tell from it whether repeated calls are safe, how long a download takes, or what happens on mirror failure.

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 model_id parameter is already documented with concrete examples in the schema. The description adds no additional meaning about accepted ID formats or validation beyond what the schema provides, 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?

States a specific verb ('Download') and resource ('open-weight model files'), plus the source ('upstream mirrors') and destination ('local models directory'). This clearly separates it from siblings like list_available_models and recommend_model, though it never names them explicitly.

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?

'On demand' hints at a trigger but gives no real when-to-use guidance: no mention of needing a model_id from list_available_models or recommend_model first, no note on whether to check if the file already exists, and no 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?

No annotations are supplied, so the description carries the full burden; 'Retrieve' implies a read-only, non-destructive operation and the mention of print sizing at 300 DPI hints at derived rather than stored values. It does not state behavior for missing/unsupported files, accepted formats, or whether files are modified — modest gaps for a simple read tool with an output 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?

A single front-loaded sentence with no filler, and the field enumeration is informative rather than redundant. Slightly list-heavy, but nothing needs trimming.

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 tool is simple (one required path parameter) and has an output schema, so return values need not be restated. The description is sufficient for correct invocation; only minor behavioral details (formats, error cases) are 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?

Only one parameter, and schema coverage is 100% with a clear description ('Path to the image file to inspect'), so the schema does the work. The description adds nothing about path form (relative vs absolute) or supported image extensions, 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?

The description uses a specific verb and resource ('Retrieve comprehensive image metadata') and enumerates the returned fields (resolution, megapixels, aspect ratio, file size, color space, print sizing). This clearly separates it from mutation siblings like upscale_image, though it never explicitly distinguishes itself from calculate_print_dpi, whose DPI/print-sizing territory it partially overlaps.

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 by the name and the 'inspect an image file' framing; there is no explicit when-to-use statement, no exclusions, and no pointer to calculate_print_dpi for dedicated print-DPI computation. An agent can infer the context but must reason about the overlap itself.

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?

No annotations are supplied, so the description carries the full behavioral burden. It signals a passive inspection of the machine's environment, but never explicitly states it is read-only/non-destructive, whether it can fail or return partial results (e.g. Vulkan unavailable, no GPU detected), or whether it requires elevated permissions. The enumerated fields do give a reasonable picture of the behavior.

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 a tight enumeration and no filler. Every listed item is substantive information about what the agent will get back.

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 diagnostic with an output schema, the description covers the important ground by naming the data categories returned. The remaining gap is failure/edge-case behavior (missing Vulkan, no discrete GPU), which the output schema may or may not express.

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 baseline of 4 applies. The description correctly makes no attempt to describe inputs.

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 ('Check') and enumerates the concrete resource fields returned: hardware profile, OS, CPU thread count, Vulkan status, GPU acceleration. This clearly separates it from the image/model-focused siblings (upscale_image, download_model, list_available_models). It stops short of an explicit contrast statement, but the domain difference is obvious.

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: an agent can infer this is a pre-flight hardware probe, plausibly useful before recommend_model or download_model. There is no explicit 'use when' clause, no mention of whether it should be called once per session or cached, and no stated preconditions.

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 discloses that each entry carries installation status, VRAM requirements, and ideal media targets, which implies a read-only catalog read. It does not state whether the catalog reflects locally installed state only or a remote catalog, nor whether the call is expensive or cached.

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, and the returned-field list is appended where it adds value. It could be marginally tighter, 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?

An output schema exists, so return values need not be re-explained, and the description still summarizes them usefully. For a zero-parameter, read-only list tool this is nearly complete; only the sibling-routing context 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 there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies no filtering options exist, since it promises 'all' models.

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 ('List') and resource ('all supported models in the catalog'), and adds the fields surfaced per entry. It does not explicitly position itself against siblings like recommend_model or download_model, so an agent must infer the boundary.

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?

Use is implied by 'list all supported models', but there is no explicit when-to-use or when-not-to-use, and no pointer to recommend_model for selection advice or download_model for installing an entry. The catalog-reading role is guessable, not stated.

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 must carry the full behavioral burden. It usefully discloses that the tool inspects host hardware locally and classifies the image (photos vs illustrations), but it never states that the operation is side-effect-free, or whether a recommended model must first be fetched via download_model. That ambiguity about a possible write step is a real gap for an unannotated tool.

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 leads with what is inspected and ends with what is produced. Every clause carries information; the only minor cost is the slightly run-on enumeration of inputs.

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 both parameters are documented. However, for a tool that sits between hardware diagnostics and model download/upscaling siblings, the description does not establish prerequisites or workflow position, leaving the agent to guess the sequence.

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 both parameters are already documented, making 3 the baseline. The description adds meaning to image_path by explaining it is used for photo-vs-illustration classification, but says nothing about how the priority parameter ('balanced', 'speed', 'quality') changes the recommendation.

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 specific verbs (inspect, recommend) and a concrete resource (model, preset, tile size), plus the evidence it uses (GPU specs, VRAM tier, CPU threads, image characteristics). This separates it from pure-lookup siblings such as list_available_models or get_image_metadata, though the overlap with get_system_diagnostics is not explicitly addressed.

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: the tool clearly belongs at the start of an upscaling workflow, but there is no explicit when-to-use statement, no exclusion of alternatives, and no mention of how it relates to get_system_diagnostics or download_model. The agent must infer the ordering and the routing.

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. It usefully discloses the Vulkan GPU vs multi-threaded CPU fallback behavior, which is real added context, but omits that this is a write operation producing a file, whether an existing output is overwritten, and the dependency on model availability.

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 front-loaded sentences with no redundant wording: the first states the action and targets, the second states the runtime behavior. Nothing needs trimming.

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 not be explained, and the schema fully covers parameters. The description covers hardware selection behavior well; the only meaningful omission is the prerequisite relationship to the model-listing/downloading siblings.

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 seven parameters are already documented in the schema. The description only echoes the target presets and adds no syntax, constraint, or interaction guidance beyond that, 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?

The description gives a specific verb (upscale), resource (image), and named engine (UpscaleX) with the supported targets (8K, 16K, 4x, custom). No sibling tool does anything similar, so an agent can distinguish it immediately from get_image_metadata or recommend_model.

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 implied: call this when you need a resolution increase. However, it never states prerequisites, such as whether the referenced model must first be fetched via download_model or validated via recommend_model, nor when not to use it.

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