workflow_reconcile

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

With no annotations, the description carries the full burden and does state the mutation direction (disk into the OS), the telemetry ingested (tokens/duration/per-agent), and idempotency. It doesn't cover permissions, failure handling, or what happens to runs already present beyond the idempotency claim.

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 repair scenario is front-loaded in the first sentence, the technical detail about what is scanned and ingested follows, and the safety claim closes it. There is no waste.

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?

An output schema exists, so return values needn't be explained, and the two params are documented in the schema. The description covers the core scenario and side effects; minor gaps are error behaviour and results when no runs are found.

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 coverage is 100% and both optional params are fully documented there, so the baseline of 3 applies. The description never mentions session_id or project_dir scoping, so it adds nothing beyond the schema.

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 ('Reconcile') and resource (finished Workflow runs on disk) plus the scan location pattern (projects/<slug>/*/workflows/wf_*.json), which an agent can distinguish from workflow_list, workflow_get, and usage_reconciliation.

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 when-to-use is explicit: repair after the OS was offline. It also states it is idempotent and safe to re-run, removing hesitation about repeats. It does not name a sibling alternative to use instead when the OS was never offline.

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