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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, but the description adds substantial behavior: the tool never fetches the page, never spends quota, returns nothing for unaudited URLs, uses the most recent stored audit, and orders fixes by expected point recovery. No contradiction with annotations exists.

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?

Every sentence earns its place: the main function is stated first, followed by clear usage directives, an exclusion, a failure mode, and cost behavior. The description is information-dense without redundancy or 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?

Even without an output schema, the description tells the agent what the result will look like (an ordered work plan with fixes and expected points), the prerequisite for successful invocation (URL previously audited), the failure behavior (returns nothing), and the remediation path (call lekta_audit first). Nothing essential is missing for correct selection and invocation.

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?

The input schema already documents the url parameter (absolute http(s) URL that was audited before), so the baseline is 3. The description adds meaningful parameter behavior: the URL must have a stored audit, otherwise it returns nothing and lekta_audit must be called first. It also clarifies the URL maps to the most recent stored audit.

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 uses a specific verb and resource: it turns the most recent stored audit of a URL into an ordered work plan, listing fixes with recoverable points and hardest-hitting first. It explicitly contrasts itself with measurement tools, distinguishing it from siblings like lekta_audit.

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 gives explicit when-to-use guidance ('USE THIS to decide what to change before touching the code'), explicit when-not-to-use guidance ('DO NOT use it to measure'), and names the alternative action ('call lekta_audit first'). This leaves no ambiguity about tool selection.

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