inspect

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

Annotations already declare readOnlyHint, idempotentHint and closed-world behavior, so the safety profile is covered. The description adds that output is textual and enumerates the returned data, which is useful, but it does not say what happens when no handles are given (that lives only in 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 clauses with zero filler: the returned fields come first, followed by the output-medium constraint. 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?

With no output schema, the description does the heavy lifting by enumerating return content, which is adequate for a read-only inspection tool. The only gap is behavior when handles is omitted, which is delegated to the schema.

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?

Only one optional parameter ('handles') with 100% schema description coverage including its default ('the selection'). The description adds nothing about handle format or selection fallback, so the schema carries the meaning entirely — baseline 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 pairs the generic verb 'inspect' with a concrete resource ('entities') and enumerates exactly what is returned: DXF attributes, effective colour, bounding box, length/area, block content. 'Text only, no image' implicitly separates it from the visual 'look' sibling, though no sibling is named explicitly.

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?

Usage is only implied: the tool is for pulling full attribute data on entities. There is no explicit when-to-use/when-not, and it never names alternatives like 'find' (locating entities) or 'measure' (dimensions), leaving the agent to infer the split.

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