local_ydb_pull_image

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

Annotations already cover the readOnlyHint=false, idempotentHint=false, destructiveHint=false safety profile, so the bar is lower. The description adds value by disclosing the two-phase behavior (plan vs execute) and the conditional outcome when the image is already present. It doesn't add detail on auth needs or failure modes, but annotations+openWorldHint handle most of the burden.

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?

Single sentence, front-loaded with the purpose, and zero wasted words. The plan/execute dichotomy and the conditional jobId behavior are packed efficiently.

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 only 0 required parameters, no output schema, and full schema description coverage, the description covers the essential behavioral contract well. It explains the two modes and the fallback when the image is already present, which is adequate for a planning/execution tool. Could mention what happens on pull failure, but for an orchestration tool this is reasonably complete.

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 baseline is 3. The description explains the confirm parameter's role (must be true to start background pull, omit/false for plan-only) and the image property defaulting to the profile image. This adds meaningful context to parameters beyond the schema, though it doesn't elaborate further on configPath or profile defaults beyond what the schema states.

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 uses a specific verb+resource ('Plan or start a background Docker pull for a local-ydb image') and clearly distinguishes the two modes (plan-only vs confirm=true execution), linking to the sibling local_ydb_pull_status for follow-up. This clearly differentiates it from siblings like local_ydb_list_versions.

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?

States explicit usage conditions: without confirm=true returns plan-only commands; with confirm=true returns a jobId for local_ydb_pull_status unless already present. It indicates when to use each mode and implicitly when to use the status tool as a follow-up, covering the key decision point for the user.

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