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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower. The description adds useful context: the polling loop pattern, the terminal statuses, the output shape on success, and the performance characteristic ('under a second'). It doesn't contradict annotations.

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, front-loads the core action, and every sentence earns its place: what it fetches, what the response looks like, when to stop polling, performance, and the read-only boundary.

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 single-parameter polling tool with a rich output schema and strong annotations, the description covers everything an agent needs: how to call it, what to expect, when to stop, and how it relates to the submission tool. The output schema already documents return values, so the description doesn't need to.

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 single parameter jobId is already described as 'The job id returned by the submit call.' The description reinforces this by saying 'by its jobId' and referencing the submission tool, but it doesn't add substantial new meaning beyond the 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?

The description states a specific verb ('Fetch'), a specific resource ('a crawl job submitted by post_firecrawl_crawl'), and the key identifier ('jobId'). It clearly distinguishes this from the submission tool and other sibling tools by noting it only reads a job and cannot start one.

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?

The description explicitly says to repeat polling until status is completed, failed, or cancelled, and notes that polling is cheap and fast. It also explicitly states what this tool cannot do ('it cannot start one'), which helps an agent choose between this and post_firecrawl_crawl.

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