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

The annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds value by disclosing the shape of what comes back (folder, files, overview, PDF path), which matters because no output schema exists. It omits failure behavior for an unfinished or unknown job_id, and it says nothing about size or permission constraints on the returned files.

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?

A single sentence with zero filler, front-loaded on the action and then the contents, with no redundancy against the title or schema. Every clause earns its place by naming a returned artifact.

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 one-parameter read tool with no output schema, the description covers the important unknown, namely what the caller receives. The remaining gap is behavioral: no statement about prerequisites (job completion) or error conditions when the pack does not yet exist.

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 description coverage is 100%, and the job_id field is already documented as coming from start_campaign. The description adds no additional meaning about the id format, validity, or reuse, so the schema does all the work and the baseline of 3 is correct.

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 uses a specific verb ('Collect') and a specific resource ('a finished campaign') and then enumerates the payload: the folder, its files, the written overview, and the PDF path. That is far more concrete than a tautology. It stops short of naming a sibling such as check_campaign, so an agent must infer which tool reports progress versus which one fetches the result.

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 phrase 'a finished campaign' implicitly signals that this is a post-completion fetch, which is useful context. However, it never says explicitly to wait until the job is finished, never points to check_campaign for polling, and never explains what happens if the campaign is still running.

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