workflow_get

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

The description reveals important behavioral traits: default response is a COMPACT projection (trimmed, not missing fields), and a full archive can be extremely large (up to 268KB). It discloses that compact excerpts result/summary and projects agent rows down to specific fields plus a drill-down key. This is rich, concrete disclosure beyond any annotation (which are absent).

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 dense paragraphs, front-loaded with a one-line purpose statement followed by essential behavioral nuance. Every sentence earns its place—the size measurement and percentage breakdown are the exact evidence an agent needs to make the compact/all decision.

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?

Given the tool has an output schema (handling return-value documentation) and 100% schema coverage, the description fully covers what's needed: purpose, compact-vs-all behavior, size constraints, and drill-down key. It's complete for a retrieval tool with strong schema support.

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%, giving a baseline of 4. The description adds meaning by explaining what 'compact' actually means (trimmed rows, scalar retention, agent row projection) and gives the concrete size rationale for the limit parameter context. It doesn't over-explain since the schema already documents each parameter well.

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 clearly states the tool retrieves a Workflow run's archive (totals, summary/result, per-agent telemetry), using a specific verb+resource ('Get a Workflow run's archive'). It distinguishes itself from siblings (workflow_list lists runs, workflow_reconcile reconciles them) by being the archive/details retrieval tool.

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 explicitly explains when the compact default is appropriate versus when 'all' (full archive) may be needed, with concrete evidence (268,753-char measurement, 53% from preview fields). It doesn't explicitly name alternatives or when-not-to-use, but the compact/full distinction gives clear usage context.

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