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

With no annotations provided, the description carries the full behavioral burden and delivers substantial value: it discloses the error/warning classification (missing/forbidden layers and wrong units as errors, empty layers as warnings) and the non-obvious `passed` semantics — warnings do not fail the check. This is exactly the behavioral context an agent could not infer from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact paragraphs with zero filler. The headline capability is front-loaded in the first sentence, and the critical `passed` behavior gets its own dedicated sentence. 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?

Since an output schema exists, the description need not document return values — and it still adds value by explaining the `passed` field's meaning. The check logic is thoroughly covered. The remaining gaps are minor: the unspecified semantics of `path` and the absence of an explicit read-only guarantee for this check 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?

Schema description coverage is 0%, so the description must compensate for missing parameter docs. It implicitly maps three parameters to their checks (required_layers → missing layer errors, forbidden_layers → forbidden layer errors, require_units → wrong units), which adds meaning. However, the single required parameter `path` is never clarified — an agent cannot tell whether it expects a file path, drawing ID, or directory.

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 opening sentence states a specific verb and resource: 'Check a drawing against drafting standards.' The validation purpose is unmistakable and naturally distinguishes it from the sibling query tools (list_drawings, find_text, drawing_summary, list_layers), none of which perform standards validation.

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 usage context is clear by implication — an agent can infer this tool is for validating drawings against standards — but there is no explicit statement of when to use it versus alternatives, nor any exclusions. No sibling is named as a better fit for related scenarios (e.g., drawing_summary for a general overview before checking standards).

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 behavioral disclosure burden. It signals non-mutating behavior through 'Describe,' adds the performance trait 'cheap,' and positions the tool as a safe first step. It does not explicitly state side effects or permissions, but for a read-only summary tool the behavioral hints are strong.

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 short sentences with no filler. The first sentence front-loads what the tool does and what it returns; the second sentence delivers actionable usage guidance. 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?

Given the tool's simplicity, one required parameter, and an output schema that defines return values, the description is complete. It covers what the tool returns, when to call it, why it is the right first step, and how it relates to the other tools. Nothing important 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 schema provides only a 'path' parameter with no description, and schema description coverage is 0%. The description's phrase 'this file' implies the path refers to a drawing file, adding slight semantic clarity. However, it does not elaborate on path format or constraints, so it only partially compensates for the missing schema description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Describe one drawing') and identifies the exact information returned: DXF version, units, layer and block counts, and entity mix. It is easily distinguished from sibling tools like list_drawings or list_layers, since it targets a single drawing and provides an overview.

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 explicit usage guidance: 'Call this first.' It explains why ('It is cheap') and what to do with the result ('it tells you which of the other tools is worth calling on this file'). This directly orients the agent toward the correct workflow among the sibling 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 burden of behavioral disclosure. It usefully discloses the output mapping (each block becomes a row, each attribute becomes a column) and the block restriction behavior. But it does not explicitly state whether the tool is read-only, how blocks without attributes are treated, or what happens on missing/invalid paths.

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 sentences with no fluff: a clear purpose, a valuable transformation detail, and a parameter tip. Every sentence contributes unique information, and the purpose is front-loaded.

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 relatively simple (2 parameters, no nested objects), and an output schema exists, so return values do not need to be described. However, the missing explanation of the required 'path' parameter and the lack of explicit when-to-use guidance leave some gaps. Still, the core extraction behavior and output shape are well covered, making it adequate but not 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?

Schema description coverage is 0%, so the description must compensate for both parameters. It clearly explains the optional 'block' parameter ('restrict the extract to one block name'), but the required 'path' parameter is not described at all. Even a basic statement about what path should point to would have lifted this toward a 3.

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 ('Extract') with a clear resource ('bill of materials from block insertions and their attributes'). The row/column transformation detail makes the tool's purpose concrete and distinguishes it from sibling tools like list_drawings, list_layers, or drawing_summary, even without naming 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 ERP/PLM sentence provides an implied use case for when this extraction is needed, and 'Pass block to restrict the extract to one block name' gives a parameter-level usage hint. However, there is no explicit statement of when to use this tool versus its siblings, nor any 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?

With no annotations available, the description carries the behavioral disclosure burden. It states the search is case-insensitive, operates on a substring, and covers TEXT, MTEXT, and block attributes, giving useful detail beyond the tool name. It does not mention all limitations, but the search semantics are reasonably transparent.

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 short, front-loaded with the core action and scope, and the second sentence adds a practical usage scenario. Every sentence earns its place with no redundant 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 is adequate for tool selection and general invocation, but it leaves a key required parameter, path, under-defined. Since there are only two parameters, missing clarity on one is a meaningful gap, even though an output schema likely covers return values.

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 provides zero descriptions for path and needle, and the description does not explicitly define either parameter. 'Needle' can be inferred as the substring, but 'path' is left ambiguous, so an agent may not know whether it expects a file path, drawing ID, or directory. The description does not compensate for the 0% schema coverage.

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 ('Search'), concrete resources (TEXT, MTEXT, block attributes), and the matching behavior (substring, case-insensitive). This clearly distinguishes it from sibling tools like list_layers or extract_bill_of_materials, which serve different functions.

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?

It provides a clear use case: locating a part number or revision note when the block or layer is unknown. It does not explicitly name alternatives or give when-not-to-use guidance, but the scenario strongly implies when this tool is the right choice.

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 does disclose one useful behavioral detail: paths are resolved relative to the configured root, and 'List' implies a read-only operation. It stops short of describing recursive behavior or what 'available' means, but the core behavior is transparent enough for a simple listing 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 one short, front-loaded sentence that immediately states the action and target. Every word adds meaning, with no filler or repetition of schema names.

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: two optional parameters, an output schema for return values, and no annotations. The description plus schema tells an agent what the tool does, what inputs it takes, and the root-relative path rule; the output schema covers return-value details. A small gap is that recursive behavior is only implied rather than stated, so it is not a perfect 5.

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 clarifies the directory parameter by stating that it is relative to the configured root, which is not in the schema, but it adds no meaning for the recursive boolean beyond what the name and default already imply. This partial compensation is adequate but not thorough.

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 concrete verb ('List') and resource ('DXF files') plus the scope ('under a directory, relative to the configured root'). This clearly distinguishes it from siblings like list_layers, which operate on layers within a drawing, so an agent can tell what the tool is for.

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 usage context is implied: use this tool to enumerate DXF files in a directory, whereas siblings like list_layers and drawing_summary address different tasks. However, there is no explicit guidance on when not to use it or how to choose among alternatives, so the routing is left to inference.

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 behavioural disclosure. It clearly identifies this as a read-only listing operation that returns all layers and their attributes. It is brief but sufficient for a non-mutating list tool, although it does not mention edge cases such as empty drawings or drawing 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?

A single, front-loaded sentence with no filler. Every part of the sentence adds information about the tool's scope and output.

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 and an output schema exists, so return-value documentation is not required. However, the description does not fully specify the required path parameter, making it only barely complete for invocation; siblings like list_drawings could supply path context but that is not stated.

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 describes a single required string 'path' with 0% coverage, and the description does not explain what the path should be or how to supply it. The word 'drawing' hints at a file path, but the agent must infer the format and provenance of the path.

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 'List' and a concrete resource ('every layer in a drawing'), enumerating the returned attributes (colour, linetype, state, entity count). This makes its purpose immediately distinct from sibling tools such as list_drawings or drawing_summary.

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 intended use is implied — call it when you need layer-level details for a drawing — but there is no explicit statement of when to choose it over alternatives, nor any exclusions or prerequisites such as first obtaining a path from list_drawings.

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