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

Annotations already declare readOnly, idempotent, non-destructive. Description adds drawer-section return content and the fact that intent/platform/search/status are ignored for kind='page', which is useful filtering semantics. No auth, rate-limit, or failure-mode context.

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 what the tool returns, then kind routing, then args. Efficient and readable. Slight redundancy between the kind bullet list and the args section, but not wasteful.

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?

Covers purpose, return content, kind-to-entity mapping, and per-kind filter applicability for an 11-param tool with no output schema and low schema coverage. Could mention pagination/volume or failure behavior, but is otherwise complete.

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 only 9%, so the description must compensate and it does: kind-to-entity_id mapping, range_preset defaults, custom date requirements and format, filter applicability per kind, and status/intent allowed values are all described. It meaningfully documents an otherwise undescribed 11-parameter schema.

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?

Clear specific verb+resource: opens the crawler drawer data for one entity and enumerates the sections returned (verdict, pipeline, health, next step, traffic, diagnostics). Distinguishes the page/path/bot kinds. No explicit sibling comparison, but get_crawler_pages is referenced as the source of path/bot ids, which implicitly routes the agent.

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?

Explains when each kind applies and which filters are ignored (path/bot only), and points to get_crawler_pages(lens='paths'/'bots') to obtain entity ids. No explicit when-not-to-use, but the kind routing is strong guidance.

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