shadowgraph_repair_plan

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

Annotations already indicate readOnly, idempotent, and non-destructive, and the description adds useful behavior beyond that: the result always carries apply:false, and ambiguous cases are routed to manual_review. This clarifies what the tool actually returns and what it cannot do.

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 short sentences, with the core purpose front-loaded and every sentence adding necessary operational detail. No filler or repetition beyond what serves the agent's decision-making.

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?

The description fully covers the operational context: when to call it, what it returns, that it never applies changes, and how ambiguity is handled. Since an output schema exists, return-value details do not need to be restated.

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?

The tool has zero parameters, so there is nothing for the description to clarify. Schema coverage is trivially complete, and the baseline for zero-parameter tools is 4.

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 ('Return') and a specific resource ('the non-destructive repair plan implied by the current diagnostics'). It clearly distinguishes this from siblings like shadowgraph_validate and shadowgraph_redact by emphasizing that it only returns a plan and never applies changes.

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?

It explicitly states when to use the tool ('Use after shadowgraph_validate') and explains that the caller must execute the plan with ordinary tools because no apply tool exists. It does not spell out explicit when-not-to-use conditions, but the guidance is unambiguous enough for correct selection.

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