compile_spec

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value beyond those by clarifying that the tool returns a resolved view and overlay metadata, implying an in-memory compilation step rather than a render or persistent mutation. No contradiction exists between the description and annotations.

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?

The description is a single sentence with no filler and front-loads the primary action and output. It is concise, though it could earn a higher score by briefly addressing data_bindings or the relationship to sibling tools without adding fluff.

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?

An output schema exists, so return-value details do not need to be repeated, and annotations cover the safety profile. However, the description is incomplete for agent decision-making because it omits data_bindings semantics and any guidance on when compiling is the right step relative to validation or rendering. It is adequate but leaves clear 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 0%, so the description must compensate, but it only contextualizes 'spec' as a FigureSpec. The data_bindings parameter is entirely unexplained, and the valid forms for spec (object vs string) are left to the agent to infer. This is insufficient for a schema that provides no field-level descriptions.

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 ('Compile') and resource ('FigureSpec') and names the output ('resolved view and overlay metadata'), so an agent gets a clear sense of what the tool does. It does not explicitly distinguish itself from sibling tools like render_spec or validate_spec, but the wording is specific enough to avoid being generic.

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?

There is no guidance about when to use compile_spec versus the sibling alternatives such as render_spec, observe_spec, or validate_spec. The description states the operation but does not indicate whether compile should precede rendering, how it differs from validation, or when it would be the wrong choice.

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