Get Lighthouse SEO report

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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, yet the description adds substantial context: omitted screenshots and tables are labeled, missing devices are named explicitly, returned data is untrusted source content rather than instructions, and balance is included in the response. These are behavioral traits the annotations do not convey.

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 retrieve purpose and mostly dense, earning sentences on omissions, trust, and completion. The three trailing sentences about balance and MCP-vs-provider credit units are tangential to this specific tool and slightly dilute focus, but remain useful workflow guidance.

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?

With no output schema and a single required parameter, the description carries the return-value burden and does so: it lists what is returned, what is omitted and labeled, how missing devices are handled, and the trust status of the content. Nothing an agent needs to invoke or interpret this tool is missing.

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 100% and the schema description already clarifies reportId is the MCP id (pattern ^seo_...) and not a provider ID. The description adds nothing about the parameter, so the baseline 3 applies since the schema does the heavy lifting.

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 (Retrieve) and resource (owned Lighthouse/PSI summary) and enumerates the returned content: category scores, audit findings, explanations, metrics, completion status. It distinguishes itself from the create sibling with 'Does not run a new audit' and 'owned'. An agent can tell this getter apart from create_onpage_report without opening either schema.

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?

Gives a clear when-not ('Does not run a new audit', implying create_onpage_report for fresh runs) and explicit alternative avoidance for balance ('Do not call get_balance again when the response already includes balance'). It stops short of naming the create tool directly, so routing is implied rather than spelled out.

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