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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the description only had to add context. It does: the headless-browser fallback when no preview is open, the 'needs project open' failure mode with no-retry advice, and a note that sourcemap warnings are benign noise.

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?

Return content comes first, then the fallback behavior, then the failure handling, then the noise caveat. Every sentence carries actionable information and none restates the schema or annotations.

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 does explain what comes back (bundle and page errors) and where from, plus the notable edge cases. The only real hole is the unexplained max_chars control.

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 50%: projectId is documented in the schema itself ('Project id from list_projects'), while max_chars is undocumented everywhere. The phrase 'the end of the log' hints at tail-style truncation, which relates loosely to max_chars, but the description does not compensate for the uncovered parameter.

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 ('Returns the end of the preview's log') and scopes it to bundle and page errors, which separates it from the deploy-oriented siblings like deploy_logs. It never names an alternative explicitly, so differentiation is inferred from the word 'preview' rather than stated.

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 supplies a concrete conditional rule: if the tool reports that the project must be open in Xodia, ask the user to open it and do not call again in this task. That prevents a retry loop, though it does not say when to reach for this versus related tools such as deploy_logs.

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