analyze_radiograph

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does add some value by enumerating the four things the tool executes (geometry checks, retrieval, citations, tool traces). However, it leaves key behavior undisclosed: the output/response format, whether this is purely read-only analysis or if it has side effects (the word 'tool traces' hints at instrumentation without explaining it), and any dependency on the case/image already existing.

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?

A single sentence with zero filler, front-loaded with the verb and the resource scope. Every word contributes to meaning, and there is no redundant repetition of the tool name or schema contents.

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 tool with three parameters, no annotations, no output schema, and 0% schema description coverage, this minimal description is inadequate. It omits parameter explanations, output expectations, side effects, prerequisites, and sibling differentiation — an agent gets the gist of what the tool runs but cannot reliably predict results or call it correctly in varied contexts.

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 loosely maps to one parameter ('case ID' ≈ 'image_id', using different terminology). It never explains 'top_k' as a result-count knob or 'question' as the query string, even though 'retrieval' and 'citations' hint at plausible meanings. Two of three parameters are left to inference.

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 ('Run') with a concrete resource list ('geometry checks, retrieval, citations, and tool traces'), which clearly states what the tool does. However, it introduces terminology ('case ID') that doesn't match the schema's 'image_id' parameter, and it doesn't explicitly differentiate itself from the sibling listing tools, though the analytical framing ('checks, retrieval') does imply a contrast with the list-oriented siblings.

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?

No guidance on when to use this tool versus list_geomed_capabilities or list_available_cases. The distinction from siblings must be inferred from the verb choices (analyze/run vs. list), and there are no stated prerequisites, preconditions, or explicit exclusions. There is no sentence anywhere telling an agent when to invoke it.

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