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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing this as a safe read operation. The description adds the scope of search (by name/action/description) and the optional 'load matches' behavior, which is useful context beyond the structured annotations. No contradictions found.

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, concise sentence of about 12 words. It front-loads the action 'Search' and provides immediate clarity without wasted words.

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 search tool with an output schema and thorough annotations, the description covers the core purpose and key parameters. The only gap is the 'limit' parameter, which is minor given that output schema and annotations already provide safety and behavioral context. Overall, sufficient for an agent to select and invoke the tool.

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?

With 0% schema description coverage, the description must compensate. It explains that 'query' searches by name/action/description and 'load' optionally loads matches, but it does not mention the 'limit' parameter or clarify what 'load' entails in terms of the matches' format. The description partially fills the gap but is incomplete for all three parameters.

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 clearly states the tool's function: searching atomic tools by name/action/description, with an optional load of matches. This specific verb+resource combination distinguishes it from sibling tools, which are about project management, version control, and resource reads rather than catalog search.

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 as the go-to search tool for discovering atomic tools. It does not explicitly name alternatives, but sibling tools make it clear this is the only search-oriented tool. No exclusions are given, but the context of the tool set makes the intended use fairly obvious.

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 indicate this is mutating, non-idempotent, and non-destructive. The description adds valuable behavioral context beyond that: the operation is atomic, requires a valid preview, and commits at a specific revision/hash. This gives useful expectations about side effects and preconditions, though it does not detail failure modes or 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 a single, focused sentence that front-loads the primary action and constraints. Every word contributes meaning, and there is no redundant or vague 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?

The description captures the core behavior and atomicity but omits practical details such as what path should point to, how preview_token is obtained, and the exact meaning of 'base revision/hash'. Given the low schema coverage and lack of parameter explanations, the description is adequate but leaves important gaps for an agent to invoke the tool correctly.

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 input schema has no descriptions, and the description does not explain what 'path' or 'preview_token' actually refer to. While 'preview' in the description hints that preview_token is a preview identifier, 'path' remains ambiguous, and there is no mention of how these parameters relate to the commit operation.

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 'commit' with a clear resource ('one valid preview') and adds important constraints ('at its recorded base revision/hash'). It distinguishes itself from sibling tools like changeset_discard and revision_revert by focusing on committing a preview rather than discarding or reverting.

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 context: only commit a preview that is valid, and do so at the recorded base revision/hash. However, it does not explicitly state when to use this tool versus alternatives such as changeset_discard, nor does it mention prerequisites like generating a preview token.

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 all annotations false, the description carries the full burden of behavioral disclosure. It does disclose the key trait that the preview is immutable and that native CAD truth is unaffected, but it lacks details on idempotency, reversibility, or what happens to the preview token after discard.

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 concise sentence that front-loads the core action and adds the key qualifier about native CAD truth. Every word contributes to understanding, with no redundancy or 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?

For a simple tool with only two parameters and an output schema, the description is minimally adequate but leaves gaps. It does not mention prerequisites (e.g., existing preview) or what the response contains, and the parameter semantics are unclear. These gaps prevent full completeness.

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 input schema has 0% description coverage, and the description provides no explanation of what 'path' or 'preview_token' mean beyond the word 'preview'. It fails to connect these parameters to the tool's purpose, leaving the agent to guess how to fill them correctly.

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 the specific verb 'Discard' with the resource 'immutable preview', clearly stating the action and scope. It also distinguishes itself from sibling tools like changeset_commit and command_preview by emphasizing that it discards, not commits or previews.

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 provides clear context that the tool is for discarding a preview while leaving the native CAD truth unchanged, implying when it should be used. However, it does not explicitly mention alternatives or exclusion scenarios, so it stops short of full 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?

The description says 'Preview', implying a read-only operation, but annotations set readOnlyHint:false, suggesting the tool may not be read-only. This is a direct contradiction. No other behavioral traits are disclosed.

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, concise, and free of filler. Every word contributes to understanding the tool's core function.

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?

Despite an output schema existing, the description is too sparse for a tool with six parameters and an enum. It doesn't explain the semantics of 'action', 'target', 'arguments', or 'project_path', leaving the agent to infer critical details from the schema alone.

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%, and the description mentions none of the six parameters, the required project_path and action, or the action enum. The description adds no parameter meaning beyond the raw 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?

The description uses a specific verb ('preview') and resource ('catalog action'), and differentiates itself by noting it works without a dynamically refreshed tool list. This clearly distinguishes it from sibling tools like project_open or catalog_search.

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 gives a clear context for when to use the tool: to preview a catalog action without needing to refresh the tool list. It does not explicitly state when not to use, but the intended use case is unambiguous.

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 provide a baseline (readOnlyHint=false, destructiveHint=false), and the description confirms the mutating nature by saying 'Create'. It adds the behavioral context that the project is 'minimal' and 'native-authored', which hints at the scope and format of what is created. However, it does not disclose potential side effects (e.g., whether an existing project at the path is overwritten) or any required permissions.

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 sentence with no redundancy. It front-loads the verb 'Create' and immediately identifies the resource and purpose. Every word contributes meaning, making it an example of concise and well-structured documentation.

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?

Even though the tool is simple (2 parameters, output schema exists), the description fails to explain the key parameter 'path', which is required. The output schema may cover return values, but the agent cannot correctly invoke the tool without knowing what path should contain. The description is too minimal to be considered complete.

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?

With 0% schema description coverage, the description must compensate by explaining the parameters. It does not mention 'path' or 'name' at all, leaving the agent to infer what these mean. The only clue is the word 'Project', but the required 'path' parameter is not clarified, which is a significant gap.

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 clearly states the action ('Create') and the resource ('a minimal native-authored Garment Project'), with the qualifier 'for drafting from scratch' that distinguishes it from sibling tools like project_import and project_open. It is specific and unambiguous, leaving no doubt about what the tool does.

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 phrase 'for drafting from scratch' provides clear context for when to use this tool—when starting a new project from an empty state. However, it does not explicitly mention alternatives, such as using project_import to bring in an existing project, which would strengthen the 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?

With no useful annotations (all false), the description must disclose behavioral traits. It states that files are not parsed or rewritten, which is transparent about non-modification of source content. However, it does not explain what 'import' actually does to the project (e.g., adds references, copies, requires existing project) or whether it has side effects. This is insufficient for a write-capable 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?

The description is a single, concise sentence with no unnecessary words. It is front-loaded with the action verb 'Import' and specifies key file types. This is an appropriate size for a tool description, even if other dimensions suffer from under-specification.

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?

Given the tool has 4 parameters (2 required), no schema descriptions, and no helpful annotations, the description is far from complete. It does not address prerequisites, project state, or parameter meanings. The output schema exists but that does not mitigate the missing guidance on inputs and behavior.

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 by explaining parameters. It only hints at file types (.val and Tape) but does not mention project_path, source_pattern, name, or measurement_files. No parameter is described, leaving the agent without guidance on how to fill them.

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 clearly states the tool's function: importing native .val and optional Tape files. It uses a specific verb (Import) and resource (native file types), and the tool name project_import distinguishes it from siblings like project_create or project_open. The scope is well-defined.

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 when needing to bring existing .val or Tape files without modification, but it does not explicitly state when to use this tool versus alternatives such as project_create or project_open. No exclusions or prerequisites are mentioned, so guidance is only implied.

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, idempotentHint, and destructiveHint false, covering the safety profile. The description adds value by noting 'existing' (implying a valid path is required) and 'compact current state' (indicating a reduced, summarized output), but it does not disclose potential errors or the meaning of 'compact' in detail. No contradiction with 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?

The description is a single, front-loaded sentence that is concise and free of redundant content. Every word contributes meaning, making it efficient and easy to parse.

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?

Given the tool's simplicity (one parameter, rich annotations, and an output schema), the description is adequately complete. It states the core action and expected return. However, it could be enhanced by mentioning behavior on non-existent paths or the use of the tool as a prerequisite for other project operations, but these are not critical given available structured metadata.

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 explaining the 'path' parameter. It only implies that path points to an existing project, but provides no details about format, absolute vs. relative, or accepted project types. This is minimally helpful beyond the parameter 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 clearly states the action ('Open') and the specific resource ('existing Garment Project'), and specifies the outcome ('return compact current state'). This distinguishes it from siblings like project_create, project_import, and project_status by conveying the intent to load an existing project rather than create, import, or merely query status.

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 when to use the tool (to open an existing project) but provides no explicit guidance on alternatives or exclusion criteria. With siblings like project_status and resource_read, the description does not clarify when to prefer this tool over them, leaving usage context somewhat ambiguous.

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 and idempotentHint=true, so the safety profile is covered. The description adds useful context by listing the specific fields refreshed, but the word 'Refresh' could be slightly misleading without annotations and no further behavioral nuances (e.g., caching, network) are disclosed.

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 very concise and front-loaded with the verb, listing four relevant data elements in a single sentence. It is efficiently structured, though 'project identity' is somewhat vague.

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?

Despite having strong annotations and an output schema, the description lacks critical context: the meaning of 'path', when to use the tool, and any prerequisites (e.g., project must be open). It feels like a terse snippet rather than a complete guide for an 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?

The only parameter 'path' has no schema description, and the tool description doesn't explain what 'path' refers to (e.g., project path, file system path). With 0% schema description coverage, the description was required to compensate but failed to do so.

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 the verb 'Refresh' with a specific resource and lists the data elements (revision, content hash, GUI-dirty state, project identity). This distinguishes it from sibling tools like project_create or project_import, though it doesn't explicitly name them.

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 provides no guidance on when to use this tool vs alternatives like project_open or resource_read. It doesn't mention prerequisites such as whether the project must already be open or imported, leaving the agent to infer usage context.

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, providing a clear safety profile. The description adds minimal behavioral context by listing the artifact types that can be read, but it does not disclose return format, error cases, or auth requirements. It does not contradict the 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?

The description is a single, clear sentence that immediately conveys the tool's function. It contains no redundant words and is perfectly front-loaded, making it highly efficient.

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 a simple read operation with good annotation coverage, so the description does not need to explain safety. However, it lacks any mention of output structure or usage context, and the overlap with command_preview is not addressed. It is adequate for a minimal read tool but not comprehensive.

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 input schema has two parameters (project_path and uri) with no descriptions, and the tool description also does not explain their semantics. With schema description coverage at 0%, the description fails to compensate, leaving the meaning of 'uri' and its relationship to 'project_path' ambiguous beyond the parameter names.

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 clearly states the action ('Read') and enumerates the types of resources it applies to ('project change-set, preview, thumbnail, or content-addressed artifact'), making the purpose specific. However, it does not explicitly differentiate itself from sibling tools like command_preview, which also deals with 'preview', so it stops short of full distinction.

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 provides no guidance on when to use this tool versus alternatives. It only states what the tool does without mentioning exclusions, prerequisites, or scenarios where a sibling tool would be more appropriate.

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 are all false (readOnlyHint=false, etc.), so the description must carry the transparency burden. 'Append' implies a write operation, but there is no detail on side effects, permissions, reversibility, or what 'reverse revision' means in practice. This is a mutation tool with minimal behavioral disclosure.

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 sentence and technically concise, but it omits critical information. It is under-specified rather than efficiently informative, so the brevity does not serve the agent's 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?

Given a 3-parameter tool with zero schema coverage and no output schema explanation, the description is grossly incomplete. It does not convey the tool's operation, when to use it, parameter semantics, or expected results, making it nearly useless for an AI 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 description coverage is 0%, yet the description provides no explanation of any parameters. It doesn't clarify the meaning of 'path', 'author', or 'revision', nor how they relate to 'native CAD preimages'. The description entirely fails to compensate for the schema's lack of documentation.

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 ('Append') and identifies a resource ('reverse revision from native CAD preimages'), but the meaning of 'reverse revision' is jargon-like and not clearly explained. It doesn't distinguish from sibling tools like changeset_commit or resource_read, and the purpose remains ambiguous without inferring from the tool name.

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 guidance is provided about when to use this tool versus alternatives. The description does not mention prerequisites, context, or exclusions, leaving the agent to guess based on the name.

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