fs_inspect

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds critical context beyond them: it explicitly states 'never content' and mentions a 'short-lived inspection token'. This is meaningful behavioral disclosure and doesn't contradict 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 sentence that front-loads the primary action and key limitation. Every word earns its place, with no fluff 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?

Despite having an output schema, the description is too sparse for a tool with 5 parameters. It doesn't explain what 'classify' means, what the reasons represent, how the token is used, or the significance of 'locally'. The complexity warrants more detail than a single sentence.

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 schema description coverage at 0%, the description must compensate, but it provides no direct explanation of any parameter. It hints at a 'bounded file range', which maps to line_start/line_end, but doesn't clarify platform/distro or other semantics, leaving agents to guess.

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 verb 'classify' and resource 'bounded file range', with a specific output of reasons and an inspection token. It distinguishes from fs_read by emphasizing 'never content', but does not explicitly differentiate from other siblings like fs_stat or fs_list, so it's not a 5.

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 explicit guidance on when to use this tool versus alternatives. It implies usage for classification without returning content, but does not state scenarios, exclusions, or reference sibling tools. Agents have to infer when this 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.