local_ydb_graphshard_check

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

Annotations already provide readOnlyHint, idempotentHint, non-destructive, and openWorldHint, so the safety profile is covered. The description adds behavioral context by naming the internal mechanism ('viewer/json capabilities and tabletinfo'), the scope ('for the configured tenant'), and the outcome details. It does not overstate side effects and matches the read-only annotation.

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?

One sentence that packs mechanism, scope, return value, and usage condition without fluff. The read-only nature is front-loaded, the output specifics follow, and the when-to-use clause is at the end. Every phrase earns its place.

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 check with fully documented parameters, annotations covering safety, and no output schema, the description is reasonably complete. It clarifies the mechanism and the specific question it answers. It could be improved by noting what failure modes look like or which sibling tool to try for broader tenant health, but these are marginal gaps.

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 the baseline is 3 even though the description adds no parameter-specific explanations. The description implies the configured tenant is read from config, but it does not name profile or configPath; the schema already documents both fully. No additional semantics are needed beyond what schema provides.

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?

Description states a specific verb and resource: 'Read-only GraphShard check through viewer/json capabilities and tabletinfo for the configured tenant.' It names the exact artifacts returned and indicates the tool is scoped to tenant. It does not explicitly distinguish from sibling tools like local_ydb_tenant_check or local_ydb_nodes_check, but the specialized GraphShard focus makes it identifiable.

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?

Use-after-tenant-bootstrap is stated explicitly, with a condition: 'when GraphShard support or tablet visibility is the specific question.' This implies when it should be used and helps differentiate from broader checks, though it does not explicitly list sibling alternatives to avoid. Clear enough for an agent choosing among related checks.

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