read_figure

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the returned resolution (~768px long edge) and token cost (~256-400), and clarifies it returns a down-scaled thumbnail rather than the full-resolution image or whole page. It does not touch on permissions or whether the source note must already be indexed, but the cost/output disclosure is strong.

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?

Front-loaded with purpose and routing before the args, which is the right order. The 'Args:' block partly duplicates what could live in the schema, but the added example and cross-reference justify it; sizing is appropriate.

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 2-param read tool with no annotations and no output schema, the description covers purpose, selection criteria, both parameters, and the shape/cost of the return value. Only minor gaps (e.g., preconditions like an existing extracted figure) remain.

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 0%, so the description must compensate, and it does: note_path is documented as a vault-relative path with a concrete example, and fig_index as a 0-based index cross-referenced to search_figures. This meaningfully exceeds a bare restatement of the param names.

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 ('Load ONE extracted figure as a down-scaled image') and situates it on a named 'recall ladder' between text search and full-page rendering. This lets an agent distinguish it from search_figures and read_note_as_image without opening either schema.

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 states the condition that selects this tool ('Use this only when search_figures' text proxy ... can't answer the question') and names the alternative it is preferred over. Decision criteria are concrete rather than inferred.

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