Image Candidates

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: token-based accent-insensitive matching across specific fields, automatic exclusion of dummy captions, copyright headers and tiny logos, and ranked output with namespaced filenames. It omits error conditions, what a missing or malformed catalog_path does, and how max_results truncation interacts with ranking.

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 the core action, then matching method, then filtering, then output, then the enum values — a logical progression with no filler. It is dense but every clause adds information, with only minor redundancy in enumerating return fields already covered by the output schema.

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 output schema means return values need not be described, and the description covers matching and noise filtering adequately for a retrieval tool. However, for a five-parameter tool with zero schema documentation, the absence of any explanation of catalog_path (the key prerequisite for calling it) and max_results leaves a real gap.

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 partially does by spelling out item_type's three values and explaining the default noise-filtering behavior that include_noise controls (though the flag itself is never named). catalog_path, query, and max_results receive no explanation at all, leaving three of five parameters undocumented in both schema and description.

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 pair (rank and retrieve) and a specific resource (figure and table entries from an extractor catalog), which is far more informative than the title 'Image Candidates'. It does not explicitly name a sibling tool or state how it differs from media_figure_build or image_namespace, so differentiation is left implicit.

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 implies the use case (finding relevant figures/tables for a query) and notes that noise is filtered by default, which hints at the include_noise toggle. It never says when to prefer this over the sibling build/namespace tools, nor when a query is inappropriate, so the agent must infer the selection context.

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