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

Annotations already mark the tool readOnly, idempotent, non-destructive, and closed-world. The description adds useful behavioral context beyond those annotations by clarifying that it 'reads stored state only' and does not produce a 'fresh measurement,' which is important for an agent deciding whether results are current.

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?

The description is compact and front-loaded: the core listing behavior and returned fields appear in the first sentence, followed by use-case guidance and an explicit cost/parameter note. No sentence is wasted, and the formatting calls out the key caveat with 'DO NOT expect...'.

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 zero-parameter, read-only listing tool with no output schema, this description is complete: it explains what is returned (sites with grade, score, and scheduled-recheck setting), the stored-state limitation, and the account-scoped context. There are no missing behavioral or input considerations an agent would need to call it correctly.

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?

With zero parameters and an empty input schema, there is nothing for the description to explain; the baseline for a no-parameter tool is 4. The description reinforces this by noting 'takes no parameters,' so an agent will not invent arguments.

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 precise verb and object: it 'Lists the sites saved on the authenticated Lekta account' and names the specific fields returned (grade, score, scheduled-recheck setting). This distinguishes it clearly from siblings like lekta_audit or lekta_report, which target auditing and reporting rather than simply reading saved state.

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 instructs when to use the tool: 'USE THIS to see what this account already tracks before auditing something new.' It also gives exclusions, warning not to expect sites from other accounts or a fresh measurement, which routes the agent away from inappropriate expectations and toward sibling tools for those needs.

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