list_jobs

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

Annotations already cover read-only, idempotent, non-destructive, and open-world semantics, lowering the bar. The description adds genuine value beyond those: the 'newest first' ordering behavior and the constraint that only 'documented terminal status' (succeeded/failed) can be used as a filter, implying non-terminal statuses are not filterable. This is useful behavioral context that annotations do not provide.

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 front-loaded sentence with zero waste. The verb comes first, ordering is stated, and the filter capability follows. Every element earns its place with no redundant phrasing.

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?

The description covers the core behaviors (ordering, filtering) and an output schema exists, so return values need no explanation. Minor gaps remain: pagination via limit/offset is not mentioned and the phrase 'documented terminal status' assumes the agent knows which statuses are terminal, though the schema's enum (succeeded/failed) makes this discoverable. Adequate for a list tool.

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 0%, so the description must compensate. It does partially address two of the four parameters: 'filter by workflow' maps to workflow_id and 'status' maps to the status param. However, the pagination parameters (limit and offset) are never mentioned, leaving half the schema undocumented in prose. The description helps for the filter params but not the paging params.

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 ('Read') with a specific resource ('jobs') and adds the ordering behavior 'newest first'. It distinguishes from siblings by being a plural list operation versus get_job/cancel_job, though it does not explicitly name those alternatives. The optional filter mention adds precision about scope.

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 context on what filters are available ('optionally filter by workflow or documented terminal status') but provides no explicit when-to-use guidance or exclusions, and does not route the agent toward get_job for single-job retrieval or list_workflows for workflow listing. The usage context is implied rather than stated.

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