참고자료 수집

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

Annotations already disclose open-world, non-idempotent, non-destructive behavior. The description adds useful context beyond that: it may consume shared usage, returns reference material rather than evidence or requirements, and explicitly rules out recursive crawling or arbitrary execution. It does not cover authentication or error behavior, but with annotations carrying the safety profile this is a solid addition.

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?

Four short sentences, each carrying distinct information: action, cost caveat, output boundary, and execution limits. The core purpose is front-loaded, and nothing is wasted.

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 simple one-parameter URL fetcher with no output schema, the description covers the essential behavioral context: what it collects, what it returns, cost, and execution limits. Annotations already handle safety hints, so the remaining minor gaps (auth requirements, rate limits) do not make the definition inadequate.

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 0%, so the description must compensate. It constrains the single `url` parameter to 'one public HTTPS reference page,' implying the expected protocol and page type beyond what the bare schema provides. It stops short of fully documenting URL format or allowed query patterns, so it is good but not exhaustive.

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 states a specific verb and resource: 'collect bounded text from one public HTTPS reference page.' It also distinguishes the output from sibling concerns by noting it returns reference material, never client evidence or approved requirements, so an agent can tell it apart from review_requirements and schema tools.

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?

Usage context is implied by constraints (one public HTTPS page, bounded text, no recursive crawl), and the description excludes client evidence and approved requirements. However, it does not explicitly say when to use this tool versus a sibling or name an alternative, so guidance remains implicit rather than directive.

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