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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real behavioral context beyond annotations: field-level precedence (agent layer beats workspace) and that missing keys/null mean 'inherit'. It does not cover return shape or the legacy include_* toggle semantics in detail.

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?

Three tight sentences, front-loaded with the operation, then the two agent_id modes, then the inheritance rule. No filler; every sentence adds semantic value.

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 tool with no output schema, the description supplies the critical return semantics (inheritance, null/missing = inherit) that an agent needs to interpret results. It could say more about the block payload structure, but coverage is strong for the complexity involved.

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 100%, so the baseline is 3. The description goes further by explaining the layering and precedence semantics of agent_id (workspace vs agent level, per-field override, inheritance), which the schema does not capture. in_workspace is left to 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?

States a specific verb and resource: 'Read the stored prompt-block overrides.' It's immediately clear this is a read operation on prompt block overrides. It does not, however, name the distinguish siblings (prompts_blocks_registry, prompts_blocks_preview), so an agent must infer the difference.

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?

Explicitly explains the two call modes: omitting agent_id returns the workspace level, providing agent_id returns that agent's layer. This is essentially when-to-use guidance driven by intent. It does not name alternative tools or describe the registry/preview siblings, so it stops short of full routing guidance.

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