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

Annotations already establish the safe read-only/idempotent profile, and the description layers on non-obvious behavior: omitted_files requiring per-file retrieval, next_offset/file_offset pagination with concatenation, license_notice_files, and the include_source=false metadata-only mode. These are real operational traits not derivable from structured fields.

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?

Front-loaded with purpose and usage before mechanics, and every sentence carries actionable content about retrieval behavior. It is dense and runs long, but nothing is filler; minor tightening of the pagination sentences would help.

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 fully carries the return-value burden: source files, SHA-256 hashes, pinned upstream revision, dependencies, author, license, and bilingual integration prompts. It also covers truncation and pagination edge cases, leaving no gap an agent would need to guess at.

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 40%, so the description must compensate, and it does for three of five params: file ('exact name'), file_offset ('repeat with file_offset until null and concatenate'), and include_source ('metadata only'). The id param's provenance is implied via the reference to search_ui_templates, but language ('zh'/'en' for the integration prompt) is never explained despite being the only enum.

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?

States a specific verb and resource ('Retrieve a curated UI template') plus the keying mechanism ('by its search result id'), which distinguishes it immediately from the sibling search_ui_templates. An agent can tell what this returns without opening the schema.

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?

Explicitly names the triggering situations ('relevant new page, replacement, substantial redesign, or reusable component') and the sequencing rule ('call this before implementation rather than stopping at the search summary'), which routes the agent away from the search tool's terminal state. This is the when-to-use guidance most definitions lack.

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