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

Annotations already mark destructiveHint=true, but the description adds meaningful behavioral context: save-time checks validate recognized Wbuilder files before any entry is written, Preview performs full compilation, and delete_missing causes soft-deletion while preserving managed/generated files. It also discloses the response's dashboard_url/public_url behavior, which is beyond annotation coverage. 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 description is dense but purposeful, with every sentence adding actionable information. It front-loads the core purpose, then covers Wbuilder constraints, validation behavior, binary routing, delete semantics, and response link handling. No filler or redundant restatement of the tool name.

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?

For a high-complexity tool with 5 parameters and destructive behavior, the description covers all critical operational context: prerequisites (AGENTS.md), editable paths, concurrency token source, validation behavior, exclusion of binary files, delete_missing semantics, and what to show the user (dashboard_url). The output schema exists, so return-value details are already covered structurally, and nothing essential is missing.

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%, so the baseline is 3. The description goes further by clarifying parameter usage: expected_bucket_revision_id should come from bucket_get, files must be text with binary assets excluded, and delete_missing semantics are explained. It also adds practical detail about content types and revision comments without repeating schema content verbatim.

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?

Description starts with a specific verb and resource: "Write multiple TEXT website files ... in one bucket edit." It immediately distinguishes itself from single-file write tools by emphasizing "multiple" and explicitly excludes binary assets, routing them elsewhere. The wording makes it clear this is the batch text-file writer for buckets.

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?

Provides explicit when-to-use guidance: for Wbuilder, read AGENTS.md first, edit data/**, leave _config/** read-only, and pass expected_bucket_revision_id from bucket_get. It also names alternatives for binary assets and whole folders (CLI or REST direct-upload API) and explains delete_missing behavior. An agent receives clear direction on when this tool is appropriate versus other tools.

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