Fetch and score a source

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

With no annotations, the description carries the full burden, and it does disclose two non-obvious traits: the granular, explainable composition of the score and the side effect that results are persisted/'registered' for later use by other tools. It omits failure behavior for unreachable or paywalled URLs, crawl timeouts, and any rate limits, so it is good but not exhaustive.

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?

Two dense sentences, front-loaded with the action and result, followed by the integration note. Every clause (score range, sub-signals, registration) carries information; nothing is redundant filler.

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 describe returns — and it does, naming the 0-100 scale and the individual signals that make the score explainable, plus where scores go next. It is nearly complete for a simple one-parameter tool, with only error/edge-case behavior left unstated.

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 100% and the single source_url parameter is already fully documented in the schema, so the baseline of 3 applies. The description's phrase 'one source URL' only reinforces the single-URL scope; it adds no format, validation, or constraint detail beyond 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?

States a specific verb (crawl/fetch and score) on a specific resource (one source URL) and enumerates the return payload: a 0-100 score plus primary-source, freshness, paywall and conflict-of-interest components. It also positions itself against the siblings by naming build_report/check_report as consumers of the registered scores, so an agent can tell it apart from those 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?

The description hints at pipeline placement by noting scores are 'registered for use in build_report/check_report', which implies this runs per-source ahead of report building. However, it never states when to use it versus plan_research or how many sources to process, and gives no exclusions or prerequisites — usage is only implied.

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