analyze_results

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does state what the tool returns (R1, wR2, GooF, max shift/esd, atom count, warning lines), which gives agents confidence about the outcome. However, it doesn't disclose behaviors like what happens if no valid refinement data is found, whether it requires one or both files, or any edge-case handling. No contradiction with annotations since none exist.

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 compact at roughly two sentences, with the return-value detail front-loaded into the first sentence. Every sentence earns its place by conveying purpose and output expectations. Minor waste is the vague phrase 'SHELXL' which could be slightly expanded, but overall it's efficient.

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 tool has a modest complexity (2 optional params, output schema exists) and the description is reasonable but not comprehensive. While the output schema exists, which reduces the need to describe return values, the description doesn't explain the relationship between the two optional input parameters or what happens when only one is provided. For a tool with this complexity, it's adequate but has clear gaps in usage context.

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 carries full parameter documentation burden. The description mentions both 'lst' and 'res' files by name ('from SHELXL .lst and/or .res text') which maps to the two parameters, but it doesn't explain their format, required vs optional status details, or whether one is sufficient. The parameters have generic titles ('Lst', 'Res') with no schema descriptions, so the tool description's brief mention is minimal compensation.

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 states a clear purpose: 'Summarise refinement metrics from SHELXL .lst and/or .res text' with a specific verb (summarise) and resource (refinement metrics files). It lists the specific metrics returned (R1, wR2, GooF, max shift/esd, atom count, warning lines), which distinguishes it from sibling 'analyze_solution'. However, it doesn't explicitly differentiate from 'analyze_solution' by name.

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 usage context (analyzing SHELXL output files) and mentions it handles both .lst and .res files. However, it doesn't explicitly state when to use this vs 'analyze_solution', nor does it provide exclusion criteria or explain the relationship between the two input files (whether to provide both, or either is sufficient) or prerequisites for usage.

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