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

With no annotations supplied, the description carries the full burden and does disclose non-obvious behavior: shared files are sent once rather than duplicated per section, tsx output has no props, html output has Tailwind classes expanded, and standalone sections are the only flat-exportable unit. It omits things like size limits on the response, ordering guarantees, or failure behavior for unknown ids.

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?

Information is front-loaded: the return contract first, then batching advice, then format semantics, then the parts caveat. It is dense but every sentence carries distinct payload or format information; the opening sentence is a fragment and the 'fundations' typo slightly hurt readability.

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?

There is no output schema, so the description must explain returns and it does: the file set per section, the write path per file, shared-file deduplication, and the exact difference between the two flat formats. Combined with a fully documented three-parameter schema, an agent has enough to call this 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 coverage is 100%, so the baseline is 3, but the description genuinely elaborates on 'format' by mapping each value to output shape and target frameworks, and by warning that only standalone sections exist for flat export. The 'have' parameter is not mentioned at all, so deduplication is explained only in the schema.

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 makes clear that this tool returns sections together with every asset file each needs plus the write path for each file, and that shared files are de-duplicated. It is written from the payload's perspective rather than a leading verb, and it never names the sibling tools (search_sections, get_design, get_theme_setup) so an agent must infer the boundary from the schema's note that ids come from search_sections.

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?

"Ask for the whole page in one call" is an explicit batching instruction, and the format paragraphs give a clear decision rule keyed to the target framework (Next/Vite/Remix vs Vue/Svelte/plain HTML). It also states a hard limit — parts have no flat export — but gives no guidance on when to prefer this over get_design or get_theme_setup.

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