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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety and idempotency profile is fully covered structurally. The description does add one genuinely useful behavioral fact - results are scoped to the linked Market Brew account's visibility - but says nothing about what "progress" states are returned, whether this is a polling operation, or how fresh the data is.

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?

Two short sentences with no filler, and the usage condition leads. Size is appropriate for a simple read tool, though the brevity comes partly from under-specification rather than discipline.

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, 0% parameter coverage, two required undocumented parameters, and a crowded deep-crawl namespace, the description leaves real gaps: what fields come back, what the two arguments mean, and how this differs from sibling retrieval tools. It is not wrong, simply insufficient for the complexity of the surrounding surface.

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?

Both required parameters (website, importId) have 0% schema description coverage, and the description never explains what either one means, what format importId takes, or whether website accepts a domain name, URL, or numeric ID. The schema's anyOf string/number unions make the ambiguity worse; the description should have compensated and does not.

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 sentence names a recognizable verb+resource (get crawl seed import progress), so the intent is inferable, but it is framed as a usage trigger that essentially restates the tool name and title. It makes no attempt to separate this from closely related siblings such as get_deep_crawl_seed, list_deep_crawl_seed_attempts, or get_deep_crawl_schedule, so an agent must open the schemas to tell them apart.

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?

It gives a trigger ("when the user asks to get crawl seed import progress"), but that trigger is circular - it says to use the tool when someone asks for exactly what the tool is named after. No alternative tool, prerequisite, or when-not-to-use condition is mentioned, despite five other deep-crawl tools in the sibling list.

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