Collect project assets

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

Goes well beyond annotations by clarifying that the scan is read-only but writing out_manifest may overwrite an existing file, which explains the readOnlyHint=false and destructiveHint=true annotations. Also discloses that file-par detection heuristics are UNVERIFIED across TD builds and that style_supported records reliability. No contradiction with 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 first sentence front-loads the core purpose, and the rest provides necessary safety and reliability caveats. Longer than average but every sentence carries information essential for correct invocation and expectation-setting. Could be tightened slightly but not wasteful.

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?

Given the tool's moderate complexity and the existence of an output schema, the description covers purpose, safety, parameter behavior, and reliability of heuristics. It fully explains what will be reported and the side effects, making it complete for an agent to select and invoke correctly.

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 already covers all three parameters with descriptions (100% coverage), baseline is 3. Description adds meaningful context by warning that out_manifest may overwrite and by explaining the heuristic fallback behavior related to par.style, which enriches understanding of parent_path and output behavior.

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?

Clearly states a specific action: scan a COMP subtree for external file dependencies and report each referenced file, the referencing node+parameter, and file existence. Distinguishes from siblings like make_portable_tox or bundle_dependencies by emphasizing it only reports and does not copy/rewrite the network.

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?

Implies usage by describing the read-only scan and optional manifest write, and hints at a contrast with tools that copy dependencies, but does not explicitly state when to use this tool over alternatives or provide exclusions. The guidance is context, not direct instruction.

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