website_changes

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

Goes well beyond the annotations: discloses the SANDBOX/dummy-data behavior, no payment, no JavaScript rendering, main-topic-only extraction, truncation of both page text and change list, and an explicit prompt-injection warning that third-party page content is untrusted data. It even enumerates the return keys, which matters since there is no output schema.

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 the core action and the comparison semantics, then conventionally ordered constraints, return keys, and caveats. Some redundancy ('Main-topic text only' and 'Truncated text does not cover the whole page') and a long clause chain make it denser than needed, but almost every sentence carries actionable information.

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 two-parameter, no-output-schema tool with a nested object, the description supplies the return shape, sandbox behavior, rendering limits and safety caveats. The one missing piece is how the caller obtains the initial 'previous' snapshot (e.g., via website_content), which an agent must infer.

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% – the nested previous.url/previous.text fields carry no descriptions in the schema – but the description compensates by defining 'previous' as a snapshot 'for the same URL' and clarifying that comparison operates on bounded main-topic text. It does not state the text size/format expectations for previous.text (12000 char cap), leaving one gap.

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 ('Fetch one page once and compare its bounded main-topic text with a caller-supplied previous snapshot for the same URL') and names the concrete output ('Reports added/removed lines'). It also negatives scope away from adjacent siblings: 'No scheduler, screenshots or whole-site crawl', which separates it from website_content/page_audit style 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 'fetch one page once' and 'no scheduler' clauses tell the agent this is a one-shot comparison, not monitoring, and the explicit exclusions (no whole-site crawl, no semantic price interpretation) define when-not-to-use. It stops short of naming which sibling to call instead for crawling or monitoring, so routing is only implied.

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