get_opinion_figures

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

With no annotations provided, the description carries the full behavioral burden and handles it well. It discloses what metadata is returned (index, kind, caption, PDF page, dimensions), that captions are editorial rather than the court's text, and that an empty list is returned both when an opinion has no figures and when figures.db is not installed. This gives an agent important expectations without needing structured 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 densely informative with no filler. The primary action and scope appear in the first sentence, followed by return-type details, a clear pointer to the image-fetching sibling, and edge-case behavior. Every sentence adds meaningful guidance.

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 single-parameter listing tool with an output schema present, the description is complete. It covers what the tool returns, how it differs from the image-fetching sibling, caption provenance, and empty-list behavior including the missing-database case. An agent has enough information to decide when to use it and what result to expect.

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 schema fully documents the citation parameter. The tool description does not add new parameter details beyond mentioning citation in the sibling call, but it doesn't need to because the schema already provides the citation format. This matches the baseline expectation for a fully covered 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?

The description opens with a specific verb and resource: 'List the figures reproduced in an opinion,' and clarifies the scope with concrete examples like plat maps, survey drawings, photos, diagrams, and tables-as-image. It also explicitly distinguishes itself from the sibling get_opinion_figure_image by stating that this tool returns metadata and that the sibling fetches actual bytes.

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?

The description gives useful context: it is for listing figure metadata, and it directs the agent to get_opinion_figure_image(citation, fig_index) for actual image bytes. It does not explicitly list exclusions or formal when-not-to-use conditions, but the sibling pointer effectively routes between the two figure-related tools. The mention of tables-as-image also implies a distinction from get_opinion_tables, though this is not spelled out.

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