check_standards

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.