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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: output is decoded as a string, the output_truncated flag is explained, and the storage retention policy is disclosed with conditions (live endpoint serve runs keep only the first few KB; run_workflow/preview runs store in full). This surfaces a real gotcha the agent needs to interpret results correctly. No contradiction with annotations.

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?

All three sentences earn their place: the first front-loads purpose and return payload, the second discloses the truncation caveat with the remediation, and the third states the storage rule for user-triggered runs. No redundant or filler content; appropriately sized for a single-parameter tool with one meaningful behavioral caveat.

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 read-only, single-parameter tool with 100% schema coverage, an output schema present, and safety annotations in place, the description covers everything an agent needs to call it correctly: what is returned, how the output is decoded, what the truncation flag means, and when the stored output may be incomplete. No meaningful gap remains.

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% — run_id is already documented as 'the run id returned by run_workflow,' so the schema carries the full burden. The tool description only restates 'by run id' and does not add format, provenance, or validation details beyond the schema. Baseline 3 is appropriate given the high coverage.

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 states a specific verb ('Get'), a precise resource ('the stored record of a past workflow run'), the key by which it is retrieved (run id), and the exact fields returned (status, content_type, output, output_truncated). This clearly differentiates it from siblings like get_workflow_run_traces (traces vs. record) and list_runs (single record vs. list), 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 clear context for when to use the tool (retrieving a stored past run record) and explicitly routes around a limitation: for runs from a LIVE ENDPOINT SERVE, the stored output is truncated, and the 're-run or preview the endpoint' alternative is named to see a whole render. It does not, however, explicitly position this tool against its closest retrieval siblings (get_workflow_run_traces, list_runs), which keeps it just shy of a 5.

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