YAMLTools

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

With no annotations, the description carries the full burden. It discloses a key behavior (source format auto-detection) and lists supported formats, but does not explain output structure, error cases, or limitations beyond input length (which is in the schema). This is adequate but not comprehensive.

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 that is front-loaded with the main action. The long list of formats is somewhat redundant with the schema enum but provides immediate context. Overall, it is efficient without excessive fluff.

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 has no output schema or annotations, and the description does not specify return values or error behavior. It covers the core functionality and a key behavioral detail, but gaps remain regarding what the output looks like and how conversion failures are handled. This is adequate for a relatively simple conversion tool but not thorough.

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. The description restates the auto-detection behavior already present in the `from` parameter's schema description ('Omit to auto-detect from content'), adding no new semantic meaning. The format list also duplicates the enum values.

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 purpose: 'Convert between data formats' and enumerates the supported formats. It distinguishes from sibling tools (diagram management, validation, visualization) as a general conversion utility.

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 usage context by explaining auto-detection of the source format and how to override it with the `from` parameter. However, it does not explicitly mention when not to use this tool or recommend alternatives, so it falls 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 no annotations, the description carries the full burden of behavioral disclosure. It mentions the operation is a save (creation), returns id and URL, may trigger a free-plan limit (paywall), and requires an API key. This goes beyond a simple 'Creates a diagram' by providing actionable context about constraints and response.

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, front-loaded with the core purpose. Every sentence provides unique info: the action, the return value, and the limitations/auth. No filler or redundancy.

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 simple nature of a create tool and the rich schema (all params defined, enum provided), the description covers the key points: purpose, authentication, paywall, and return value. It lacks details on error cases (e.g., invalid YAML) but that is often handled by schema validation. The absence of an output schema is mitigated by mentioning the id and URL.

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 already describes all three parameters with high coverage (100%), including types, constraints, defaults, and enum values. The description adds no parameter-specific meaning beyond the schema, such as what 'yaml' should contain or what each diagramType means. Baseline 3 is appropriate.

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: 'Save a new diagram to the user's account.' This clearly differentiates from sibling tools like update_diagram (modifying existing) or get_diagram (retrieving). It also notes the return value (id and URL), clarifying what the tool achieves.

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 for creating new diagrams but does not explicitly state when to use this tool versus alternatives like update_diagram or convert_yaml. There are no exclusions or alternative recommendations. The only guidance is the paywall and API key requirements, which are more constraints than usage direction.

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 provided, the description carries the burden of behavioral disclosure. It adds useful constraints (Pro feature, API key) but does not explain what happens on creation (e.g., if a folder with the same name causes an error) or the return value. It fails to disclose critical side effects or success/failure 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?

The description is highly concise, with the main action front-loaded in the first sentence and the constraints in the second. Every word earns its place with no redundant or vague phrasing.

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 mutation tool with only two parameters, the description covers purpose and prerequisites but is missing key contextual details like the return value (folder ID or object) and any error conditions. Since there is no output schema, the description should have provided at least a hint about the expected output.

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 already provides 100% coverage with descriptions for both parameters (name and parentFolderId). The description adds no additional parameter-specific meaning beyond the schema, 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 the specific verb and resource: 'Create a Drive folder to organize diagrams.' This clearly distinguishes it from sibling tools like create_diagram or delete_diagram. It also adds relevant constraints (Pro feature, API key) that further clarify the tool's scope.

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 clear context for when to use the tool (to organize diagrams) and mentions prerequisites (Pro feature, API key). However, it does not explicitly mention alternatives or when not to use it, such as noting that list_folders should be used to view existing folders or that move_diagram is for relocating diagrams.

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 provided, the description carries the full burden and discloses the critical destructive nature ('Permanently delete') and an authentication requirement (API key). This goes beyond a basic 'delete' statement and communicates the irreversible action and access prerequisite.

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 the action front-loaded. The first sentence states the operation and target; the second adds the required API key. No unnecessary 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 one-parameter delete operation with no output schema, the description covers the essential behavior, authentication requirement, and parameter. It could mention error behavior or idempotency, but these are not critical for basic usage and the description is sufficient.

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 already documents the single 'id' parameter with 100% coverage. The description adds only marginal context ('one of the user's diagrams'), but essentially relies on the schema for parameter meaning.

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 'Permanently delete one of the user's diagrams by id' — a specific verb, resource, and scope. It distinguishes itself from sibling tools like update_diagram or get_diagram.

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: it is for permanently removing a diagram by id and requires an API key, which implies the appropriate usage scenario. It does not explicitly name alternatives or exclusions, but the sibling set makes the purpose 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?

No annotations are provided, so the description carries the full burden. It discloses the return content and the API key requirement, and the verb 'fetch' implicitly indicates a read operation. However, it does not mention non-existence handling, rate limits, or other potential behaviors, which would strengthen transparency for a tool with no annotation support.

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 return value, with the API key requirement appended succinctly. Every word contributes value, 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 single-parameter fetch operation with no output schema, the description provides sufficient context: it states the exact input (id), what it returns (YAML source and metadata), and the auth requirement. It does not explain error cases, but that is acceptable given the tool's simplicity and the rich sibling context.

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% since the 'id' parameter is documented as 'Diagram id'. The description adds minimal extra meaning by clarifying the id is used to fetch one diagram and returns its YAML, but this largely restates the schema. Baseline of 3 is appropriate given the schema already covers the parameter.

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 ('Fetch') and resource ('one of the user's diagrams by id'), and specifies the return content (YAML source and metadata). This distinguishes it from sibling tools like list_diagrams and search_diagrams, which have different scopes.

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 this tool: when you have a specific diagram id and need its YAML source and metadata. It also mentions the API key requirement, providing useful context. However, it does not explicitly name alternatives or exclusions, such as using list_diagrams for all diagrams.

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 burden of disclosing behaviors. It mentions the API key requirement and clearly lists the output fields, making the read-only nature evident. However, it does not address potential pagination or sorting behaviors, which is a minor gap.

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, front-loaded with the verb 'List' and resource 'diagrams'. The parenthetical field list and auth requirement add essential information without any redundancy or fluff.

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?

As a simple list tool with 0 params and no output schema, the description sufficiently conveys the primary purpose, the fields returned, and the auth requirement. It does not specify sorting or pagination, but these are not critical for a basic listing operation.

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 has zero parameters and the schema reflects this. With 0 params, the baseline is 4, and the description adds no parameter info because none is needed. The field list in the description compensates for the lack of an output 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 clearly states the tool lists the authenticated user's saved diagrams, specifying the exact fields returned (id, title, type, visibility, updatedAt). This distinguishes it from siblings like get_diagram (single diagram) and search_diagrams (search-based retrieval).

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 for retrieving one's own diagrams but does not explicitly mention alternatives or when not to use this tool. It provides clear context (auth requirement) but lacks direct differentiation from similar list/search tools.

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 transparency burden. It states the required API key and lists the return fields, making the read-only nature and output clear. It does not mention pagination or errors, but for a simple list operation this is sufficient.

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 main purpose and includes the key return fields and authentication requirement. Every word 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 simple zero-parameter list tool, the description is complete: it specifies the resource, return fields, and auth requirement. No output schema exists, but the description sufficiently explains what to expect.

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 has zero parameters and the schema coverage is 100%, so the baseline for parameter semantics is 4. The description adds no parameter detail because none is needed.

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 ('List') and resource ('the user's Drive folders'), and specifies the included fields (id, name, parentFolderId). This clearly distinguishes it from sibling tools like list_diagrams.

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 clearly indicates this tool is for listing the user's Drive folders and notes the API key requirement. It does not explicitly name alternatives or exclusions, but the context 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?

With no annotations, the description carries the full burden for behavioral disclosure. It reveals the auth requirement (YAMLTools API key) and the semantics of folderId=null for root. However, it does not disclose potential side effects, such as whether the diagram is removed from its previous folder, or whether the operation is reversible. The coverage is adequate but not rich.

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 sentences, front-loaded with the core action and destination, followed by the auth note. Every word carries meaning; no filler or redundancy.

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 two-parameter move operation, the description covers the purpose, destination semantics, and auth. The only gap is that no output schema exists and the description does not mention the return value or success/failure behavior, but the core context is sufficiently complete for this low-complexity 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?

Schema description coverage is 100% for both parameters (id and folderId), so the baseline is 3. The description restates the null-for-root meaning already present in the schema, adding no new parameter semantics beyond what schema descriptions provide.

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 (move), the resource (the user's diagram), and the destination (a folder or root via null folderId). It distinguishes from sibling tools like create_diagram, delete_diagram, and update_diagram by specifying the move operation and the special null case for root.

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: this is for relocating diagrams between folders or to the root. It doesn't explicitly mention when not to use it or suggest alternatives, but the operation is well-defined and the null folderId handling is a useful usage detail. No exclusion criteria 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 provided, the description carries the full burden. It discloses a key prerequisite (requires a YAMLTools API key) and clarifies the return content (matches with their folder). The read-only nature is implied by 'search' but not explicitly stated, which is a minor gap.

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 sentences, front-loaded with the action ('Search') and includes only essential details: scope, search field, return value, and authentication requirement. No redundant or vague phrasing.

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 (1 parameter, no output schema), the description covers the core aspects: what it does, what it returns, and a required credential. It does not mention pagination or result limits, but these are not critical for correct invocation. A minor gap is the lack of explicit read-only assurance, but the search semantics make it obvious.

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%—the schema already defines query as 'Text to match in the diagram title'. The description adds no additional parameter semantics beyond repeating 'by title text', so it does not enhance the structured field info. Baseline of 3 is appropriate.

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 searches saved diagrams by title text, specifying the resource (saved diagrams), scope (authenticated user's), and search criterion. It also notes the return value (matches with their folder), which distinguishes it from siblings like list_diagrams or get_diagram.

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 explicitly indicates this tool is for searching diagrams by title, implying it should be used when a title-based lookup is needed. It does not explicitly compare with list_diagrams or mention exclusions, but the context is clear enough for an agent to choose it over siblings.

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 disclose side effects. It only mentions the API key requirement, which is useful, but it omits whether the update is partial or full, how omitted fields are handled, and what happens on invalid YAML. This is a significant gap for a mutation 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, focused sentence that states the core operation and a key prerequisite. There is no filler or redundancy, making it appropriately concise and 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?

For a mutation tool with no annotations and no output schema, the description lacks critical context such as update semantics, response behavior, and error conditions. It provides only the basic operation and auth requirement, which is insufficient for an agent to anticipate consequences.

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 schema covers all four parameters with descriptions at 100% coverage, so the baseline is 3. The description's 'source, title and/or type' adds no new meaning beyond the schema properties, which already explain each field.

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 (update), the target resource (existing diagram), and the modifiable attributes (source, title, type). This differentiates it from siblings like create_diagram and delete_diagram, which have distinct purposes.

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 for modifying existing diagrams but does not explicitly compare with alternatives or state when not to use it. The mention of 'existing diagram' gives context, but there are no direct references to create_diagram or other relevant siblings.

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 provided, so the description carries the full burden. It discloses that it reports syntax errors with line/column, lint warnings, and document stats, which is helpful. However, it does not explicitly state that the tool is read-only, does not modify input, or what happens on success/failure. For a validation tool, the behavior is reasonably transparent but could be more explicit about side-effects and return format.

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 sentences, front-loaded with the main action, and includes specific details (line/column, lint warning types, stats) without any fluff. Every 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 simple tool with one parameter and no output schema, the description provides sufficient context: it lists the types of errors and stats the agent can expect. It does not specify the exact output structure, but 'Reports...' sets clear expectations. The absence of an output schema is mitigated by the detailed description.

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 for the single parameter 'yaml' is 100%, including a description ('The YAML content to validate'). The tool description does not add additional parameter semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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: 'Validate and lint a YAML document.' It also specifies what the validation covers (syntax errors, lint warnings, stats), distinguishing it from sibling tools like convert_yaml and visualize_yaml.

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 this tool—when you need to validate and lint YAML—but does not explicitly mention alternatives or say 'use convert_yaml if you need to convert.' The clear focus on validation makes the usage context obvious, though it lacks explicit exclusionary 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 annotations, the description carries the transparency burden and does a solid job: it discloses the core return value (Mermaid source), the conditional public image requiring an API key, and the TREE/FLOW modes. It stops short of describing error behavior or exact response shape, but for a non-destructive transformation tool this is adequate.

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 three short, front-loaded sentences. Each sentence adds a distinct piece of information: core function, output/API-key behavior, and supported modes. There is no wasted wording.

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?

Because there is no output schema, the description must explain return values, and it does. It covers the essential output behavior, API-key dependency, and diagram types. It does not specify the exact response envelope or failure modes, but for a straightforward transform tool with complete parameter schema coverage this is largely sufficient.

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?

All three parameters have schema descriptions, so the baseline is 3. The description adds no meaningful parameter information beyond what the schema already provides—it merely restates the diagramType enum values without extra syntax or usage nuance.

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-object pair ('Turn YAML into a diagram') and clearly differentiates from siblings by stating it returns Mermaid source and optionally a hosted public image. It also names the two supported diagram types, making the purpose unmistakable.

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 on when to use this tool versus alternatives like convert_yaml, create_diagram, or validate_yaml. The description explains what the tool does but does not mention exclusions, prerequisites, or alternative tools for related scenarios.

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