agent_inspect

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuinely new behavioral fact — that returned metadata is untrusted data and should not be acted on as instructions — which is real value beyond the structured fields. It still omits what the inspection returns and why the limit is capped at 32.

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 fragments with zero padding and the primary purpose front-loaded, which is good. But the terseness reflects under-specification rather than disciplined editing — the security note consumes half the text while core semantics are absent.

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 and an undocumented parameter, the description must explain what is inspected and roughly what is returned; it does neither. The untrusted-data warning is the only substantive content, leaving the agent unable to predict the response shape.

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 0%: the single optional 'limit' parameter has no description, bounds explanation, or unit. The description never mentions it, so the agent cannot tell whether it limits items, bytes, or depth. With low coverage the description was expected to compensate and does not.

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?

"Compact project inspection" essentially restates the tool name (agent_inspect) without saying what part of the project is inspected or what comes back. It does not distinguish itself from siblings like agent_status, session_info, or agent_measure, which all sound like project-level reads.

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 word "compact" hints that this is the cheap/lightweight read, but there is no explicit when-to-use, when-not-to-use, or named alternative. With a dozen agent_* siblings, the agent is left to guess which inspection tool to call.

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