Attach docs as assets

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds value by specifying the exact destructive action: 'writes into the package folder (destructive).' It also discloses the registration in the manifest's docs list, providing behavioral context beyond the structured annotations. No contradiction.

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 sentences, front-loaded with the primary action, then usage context and a warning. Every word earns its place, with no redundancy or fluff.

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?

The description covers the core workflow and references make_portable_tox for context, but it omits any mention of the optional help_snapshot parameter and its nested structure. Given the tool's moderate complexity (4 params, nested object, no output schema), the description is adequate for the main use case but not comprehensive. The destructive note and usage guidance help, but parameter coverage remains incomplete.

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 description coverage is only 25% (only help_snapshot has a description). The tool description does not explain docs, asset_dir, or manifest_path; it only mentions 'docs list' indirectly. With low schema coverage, the description should compensate for parameter meanings, but it fails to clarify the array format, defaults, or required path. This is a significant gap.

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 action: 'Copy documentation files into a package and register them in its manifest's docs list.' This specifies a concrete verb and resource, distinguishing it from sibling tools like make_portable_tox or bundle_dependencies. The context 'Use after make_portable_tox' further anchors its role.

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 provides explicit usage context: 'Use after make_portable_tox to bundle a README or usage notes with a component so they travel with it.' This tells the agent when to use the tool and its purpose, but lacks explicit alternatives or when-not conditions. The guidance is clear enough for most cases.

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