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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds meaningful behavior beyond them: the response is a manifest spanning kinds, sizes, row counts, timestamps, visibility and upload status, and the run defaults to "latest" when none is specified. It stops short of noting empty-manifest, upload-in-progress, or size/pagination behavior.

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?

Purpose is front-loaded in the first clause and the artifact inventory follows immediately. The ten-item field enumeration in sentence one is somewhat dense, but every item tells the agent what it can rely on finding in the manifest.

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 description correctly carries the return-value burden by listing manifest fields and the specific artifact keys an agent should verify. For a two-parameter read tool with full annotation coverage, this is nearly sufficient; only the required deploymentId's meaning and the handoff to the single-artifact siblings remain unstated.

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 0%, so the description must carry the parameter load, and it only partially does. "Latest or specified" hints that runId is optional and defaults to the newest run, but deploymentId — the required parameter — gets no explanation of its UUID form or what happens when runId does not belong to that deployment.

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 a specific verb and resource ("Returns the manifest ... for the latest or specified deployment run") and enumerates the manifest contents, so the agent knows exactly what it gets. It implicitly separates itself from list_deployment_runs and get_deployment_artifact by scoping to a run's manifest, but never names those siblings, so the differentiation must be inferred.

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?

Explicit when-to-use is given: find canonical agent_detail and memory artifacts before asking why a live or scheduled bot made a decision, plus a concrete verification checklist (agent_detail + memory_events, memory_retrievals, memory_state) for scheduled AI-agent strategies. There is no when-not guidance and no named alternative such as get_deployment_artifact or query_deployment_artifact for fetching artifact contents.

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