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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value by disclosing the payload contents (timing, status, error, next retry), but says nothing about authentication needs, pagination of attempts, or behavior when the run is still in flight.

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 compact clauses: the returned content first, the REST endpoint second. Every element earns its place, though the sentence is a fragment rather than a full statement of purpose.

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?

With no output schema, the field enumeration is the main carrier of return-value information, which is helpful. However, for a 3-parameter tool with one undocumented parameter and no mention of auth or error cases, the description leaves real gaps an agent would want closed.

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 67%: job_id carries a format hint ('job_<ULID> returned by create_job') and management_token documents the Authorization-header fallback, but run_id has no schema description. The description's REST path template (GET /v1/jobs/{id}/runs/{run_id}) only implies how the two IDs relate, adding little 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?

The description names the resource ('one run') and its sub-resource ('each delivery attempt') and enumerates the fields returned (sent_at, response status, duration, error, next retry), so an agent knows this is a single-run detail read. It does not distinguish itself from the sibling get_deliveries, which likely overlaps in the delivery-attempt data, so it stops short of a 5.

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?

There is no guidance on when to use this tool versus get_deliveries, get_job, or list_jobs. The agent must infer that this is the drill-down for a single run, and nothing states prerequisites or exclusions.

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