scan_project

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 genuinely new behavior beyond that: the output is a small, bounded set of file:line evidence strings, and scan results confer no authorization for code changes. The negative list about not drawing or writing largely restates the annotations, which slightly dilutes the value.

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 purpose is front-loaded in the first clause, followed by scope limits and then the sibling routing advice, which is a sensible order. The four-item negative enumeration (no diagrams, no board change, no file writes, no code-change authorization) is partly redundant with the annotations and could be tightened.

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 carries the burden of describing returns and does so by noting the bounded file:line evidence. Combined with the annotations and fully documented schema, an agent has enough to call this correctly; only the concrete shape of the evidence text is left implicit.

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 100% and all three parameters (max_depth, max_files, include_evidence) carry their own descriptions with defaults and bounds. The description adds no parameter-level detail such as what evidence looks like or how max_files interacts with max_depth, so the baseline of 3 applies.

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 gives a specific verb and resource: a read-only scan of the current workspace's directories and file paths, returning bounded file:line evidence. It explicitly separates this from draw_board, so an agent can choose between the two without inspecting either schema.

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 names the alternative (draw_board) and the condition that selects it: when visualization is needed, draw the paths onto the shared board. It also frames the tool as an 'optional capability' and limits its role in the broader board discussion, but it never states a positive condition such as when a scan is the right first step.

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