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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the useful ordering fact ('newest first') and account scoping, but says nothing about pagination behavior, default page size, or what the result set contains.

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 waste, front-loading the verb and resource and ending with the ordering detail an agent needs.

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 simple read-only list tool with annotations and no output schema, the definition covers purpose and ordering. It omits that the response supplies a next_before cursor for the 'before' parameter, which is the one behavior an agent paging through results would need to know.

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?

The description adds no parameter meaning; 'before' and 'source' are documented in the schema and 'limit' carries min/max bounds but no prose (67% coverage). The remaining gap is small and largely self-evident, so this sits at the baseline rather than below it.

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?

States a specific verb and resource ('List' + 'caption jobs'), plus scope ('the account's recent') and ordering ('newest first'). This clearly separates it from get_caption_job and create_caption_job, though it does not name a sibling explicitly.

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?

Usage is only implied: 'list' plus 'recent' signals a browse/recent-activity call, and the sibling set makes the read-vs-get distinction inferable. No explicit when-to-use or when-to-prefer-get_caption_job guidance is given.

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