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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: a fixed 30-day window, a cached single JSON snapshot, OAuth authorization as the curator account, and a methodology note that bot and own-pipeline renders are classified out so headline numbers stay human-only. That is exactly the kind of behavioral detail an agent cannot get from the annotation block.

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 critical access constraint is front-loaded, but the body is a single enormous run-on sentence stuffed with nested parentheticals and internal metric definitions (detail stages, utm_campaign/utm_content mapping, mail variant fields) that go well past what an agent needs to select or call a zero-parameter tool. The information is mostly on-topic, yet the density and lack of paragraphing make it harder to scan than it needs to be.

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, the description carries the full burden of explaining return contents, and it does so exhaustively — sections returned, the llm_crawler breakdown, the single-snapshot format, and the fixed window. For a zero-input, read-only reporting tool, an agent has everything needed to call it and interpret what comes back.

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?

There are zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly does not invent input options, though it also does not state explicitly that no filtering or date-range override is accepted.

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 states a very specific resource and scope: 'autario's own traction', a single report uniting GA4 human reach, MCP/agent channel metrics, the signup and activation funnel, the buyer revenue funnel, drop-off, top charts/endpoints and per-app usage. It also names the access class ('ADMIN/CURATOR ONLY'), so an agent can tell this apart from general analytics siblings like ai_visibility_360 or audience_360 without opening a 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?

Concrete trigger phrasings are given ('how is autario doing', 'show traction', 'which datasets do agents use', 'do LLMs crawl us'), plus an access precondition — any non-curator caller gets a permission error. It lacks explicit when-not-to-use guidance or named alternative tools for narrower questions, which keeps it below a 5.

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