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

With no annotations, the description must carry behavior and does add some: the created model is a draft, the payload is validated, and the full model is returned. It omits permissions, what happens on conflict/invalid input, and whether drafts are later published — significant gaps for a mutation tool with zero annotation coverage.

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 tight clauses with the action and the argument requirement front-loaded, then the return value. Nothing 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?

The return value is covered in lieu of an output schema, and the draft nature is stated, but with no annotations and an opaque required parameter the definition leaves out error behavior and the draft lifecycle — enough for a knowledgeable caller, thin for a first-time agent.

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 0% and the single 'model' parameter is an undescribed string capped at 1,000,000 chars. The description tells the agent it holds a complete v1 JSON model, which is genuinely useful, but gives no hint about the v1 schema shape or where to find it, so an agent still cannot construct a valid value from the definition alone.

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 ('Create') and resource ('/m:os system model'), plus a distinguishing qualifier ('draft') that separates it from model_update. The v1 format is named, though it never explicitly contrasts itself with model_validate or model_get.

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?

'pass a complete v1 JSON model' implies the prerequisite that the payload must be a fully-formed v1 model rather than a patch, but there is no explicit when-to-use guidance or named alternative (e.g. use model_validate to check before creating).

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. "Export" implies a read-only operation and "standalone inline-SVG HTML" hints at the serialization approach, but it never says whether the tool returns the exported content directly, a file path, or a download reference, nor whether anything is written or mutated server-side.

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 well-formed sentence with zero filler, front-loading the action and the output choices. Brevity is appropriate, though the space saved could have been spent clarifying the return value or the model parameter.

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?

No annotations and no output schema exist, so the description is the only source of behavioral information, and it omits both the shape of the returned value and the meaning of the required model input. For an export/serialization tool where the result format is the whole point, these are material gaps.

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 usefully expands the bare "json"/"svg" enum by explaining that svg means "standalone inline-SVG HTML," which is genuine added meaning. However, the required "model" parameter (a string up to 1,000,000 chars) is left ambiguous — is it a model ID or the serialized model payload? — which is a significant omission an agent could get wrong.

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 ("Export") and resource ("supplied model") plus the output formats, which cleanly separates it from the model_create/model_update/model_validate/model_get siblings. It stops short of naming those siblings or describing the export result, but an agent can identify the tool's job from the sentence.

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 or when-not-to-use guidance, no prerequisite that a model must exist or be validated first, and no instruction on how to choose between the two formats beyond listing them. Usage is inferred from the verb "Export" alone.

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 the server is stateless, so no server-side state is created or mutated. It does not say what happens when validation fails (error shape, rejection vs. partial return) or how the 1,000,000-character limit is enforced.

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 with no waste, and the core action is front-loaded before the stateless qualifier. It is efficient, though its brevity is partly the cause of the disambiguation gap rather than a sign of completeness.

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, non-mutating tool with no output schema, the description covers the essentials of action and side effects. It still leaves the agent unsure how this differs from model_validate and what a validation failure looks like, which matters for correct selection.

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 0% for the single 'model' string, so the description carries the burden. Saying 'the complete model' adds meaning by implying a full document rather than a partial one or an identifier, but it never states the expected encoding (JSON string? raw text?) or what 'complete' structurally requires.

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 pair (validate and return) and resource (the model), but the name 'model_get' implies retrieval of a server-held entity while the description describes an echo/validate operation on caller-supplied input. It also overlaps heavily with the sibling model_validate, which is never distinguished.

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 statement of when to use this instead of model_validate, model_create, or model_update, all of which appear as siblings. The only contextual hint is the 'stateless' remark, which implies nothing is persisted, but the agent must infer that on its own.

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 discloses that the server retains no model between calls and that the operation replaces the active model, but it does not explain validation failure behavior, whether the previous model is recoverable, or any permission requirements.

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 two concise sentences with no wasted language. The core replacement behavior is front-loaded, and the statelessness detail follows immediately as supporting context.

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 mutation tool with no annotations and no output schema, the description covers the essential replacement semantics and the stateless server model. It could be more complete by mentioning validation behavior or irreversibility, but it provides enough context for correct invocation.

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 for the single `model` parameter. It adds meaningful context by requiring a complete `/m:os` JSON model rather than a partial patch, but it does not document the model structure or how validation errors should be handled.

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: replace the active visual model. It also specifies the required payload format (`/m:os` JSON), which distinguishes it from model_create, model_validate, model_get, and model_export. It stops short of naming siblings explicitly, so it is clear but not maximally differentiated.

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 by saying it replaces the active model with a complete updated model, which suggests full replacement rather than partial update. However, it does not explicitly say when to use this versus model_create or model_validate, and it gives no exclusions or prerequisites.

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 exist, so the description carries the full burden. It does say issues are returned per field, but never states that this is a non-mutating/read-only check, what input format the model string takes, or what happens on a malformed payload.

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 compact sentence, front-loaded with the verb and resource, with the return shape appended. No filler, but also little substance.

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?

No output schema exists, so the description is the only source of return information and it provides just three words ('field-specific issues'). Combined with the undocumented input format, an agent cannot confidently construct a valid call.

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 'model' parameter has 0% schema description coverage, and the description only implies it is a whole /m:os model body. It does not clarify whether that string is JSON, a DSL, or reference a stored model, which is the key ambiguity for this tool.

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 ('Validate a complete /m:os model') and adds the outcome ('return field-specific issues'). It reads distinctly from siblings like model_create and model_get, though 'complete' is left unexplained.

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 statement of when to call this instead of model_create/model_update, no note on whether validation is a prerequisite before saving, and no exclusions. Usage is only weakly implied by the verb.

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