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

Annotations already cover readOnly, idempotent, open-world, and non-destructive behavior, lowering the burden. The description adds genuinely valuable behavioral details: newest-first ordering, the recommendation to filter instead of paginate, and the instruction to follow any llmContext guidance included in results. This goes beyond what annotations alone communicate.

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 three short sentences with no filler. It front-loads the core purpose, then gives practical filtering guidance, then an important behavioral follow-up about llmContext. Every sentence earns its place.

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 a 100%-covered schema, rich annotations, and an output schema present, the description does not need to restate parameter details. It appropriately adds ordering behavior, filtering guidance, and the llmContext follow-up instruction. Slightly cryptic 'extract group' phrasing and the lack of an explicit note about nextPageToken keep it from being fully complete, but overall it is adequate for an agent to use the tool correctly.

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?

Parameter coverage in the schema is 100%, so the baseline is 3. The description repeats a few filter parameter names but does not add any deeper semantics beyond what the schema already provides. The 'filter rather than paginate' note is the only added value, but it is more of a usage strategy than a parameter definition.

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 opens with a specific verb and resource: 'List recent extract runs, newest first'. This clearly identifies the object (extract runs) and the primary behavior. It also names concrete filter dimensions (status, extractorId, batchId, fileNameContains), which helps distinguish it from sibling list_*_runs tools even without naming them.

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 gives useful in-tool guidance ('Filter rather than paginate') and tells the agent to follow llmContext guidance in results, but it does not explicitly say when to choose this tool over siblings like get_extract_run or list_parse_runs. The usage context is implied rather than explicitly contrasted with alternatives.

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