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

Annotations already establish the safety profile (readOnlyHint=true, destructiveHint=false), so the description's job is to add behavioral context beyond that — which it does: sort order ('most-recent-first'), the summary fields returned ('run_id, status, message, timestamps'), and the status filter values. No contradiction with annotations; the only omission is pagination behavior, but that is covered by the schema.

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?

Two sentences with zero waste: the core action and ordering are front-loaded, followed by the filter, the return shape, and sibling routing. Every clause earns its place, and the alternative-tool routing is packed efficiently into the final clause.

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 4-parameter list tool with an output schema and safety annotations, the description covers purpose, ordering, filter values, return summary, and sibling routing — nearly everything an agent needs. Pagination is legitimately left to the schema, which thoroughly documents page_token and next_page_token. Minor gaps like not-found behavior or empty-result semantics are acceptable given the output schema and the low complexity.

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%, so the baseline is 3. The description reinforces workflow_id as the lookup key ('by workflow id') and restates the status filter values, but page_size and page_token semantics are left entirely to the schema, which already documents them adequately ('token from a previous response's next_page_token'). The description adds modest interpretive value without needing to compensate for gaps.

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 a workflow's past runs') with a precise scope qualifier ('by workflow id') and ordering ('most-recent-first'). It also names the sibling tools it is not — get_workflow_run for output and get_workflow_run_traces for per-step detail — so an agent can distinguish it from adjacent run-related tools without opening schemas.

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?

Explicitly routes to alternatives with concrete conditions: 'use get_workflow_run for a run's output or get_workflow_run_traces for per-step detail.' The description also signals optionality ('Optionally filter by status') and enumerates the valid filter values, so an agent knows when to omit the filter entirely.

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