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

With no annotations, the description carries the full burden and does well: it discloses that the run is metered/credit-checked, that refusals happen before any credits are spent, and names two concrete refusal codes with their triggering conditions. It omits whether the call is synchronous or returns a run handle, and any permission or rate-limit context.

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, no filler, and the core action plus its cost model are front-loaded ahead of the failure modes. The second sentence is long and packs two distinct refusal cases together, slightly reducing scannability.

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 metered mutation tool with no annotations and no output schema, the description covers cost, pre-flight checks and named refusals, which is what an agent most needs before calling it. It stops short of describing the success result (run id, async behavior) and required entitlements.

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 agentKey, modelId, instructions, targetPage and requestIdempotencyKey are already documented. The description only adds semantic color for targetPage (the run 'briefs that page and no other' and can trigger target_page_refused), which is a marginal increment over the schema baseline.

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 ('Trigger a metered manual managed-agent run'), which implicitly separates it from the read-side siblings devtune_get_agent_run and devtune_list_agent_runs. However, it never names an alternative tool, so the differentiation is inferred rather than explicit.

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 implies this is the manual-trigger path and describes the failure conditions (no readable evidence, unusable targetPage), which edges toward when-not-to-use guidance. But it never says when to prefer this over the sibling run-related tools or what prerequisites (credits, agent selection via devtune_list_agents) must be in place.

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