Evaluate one or more headless CAS expressions server-side (MCP-only numeric mode). Unsupported expressions return a GUI handoff link.
| Name | Required | Description | Default |
|---|---|---|---|
| strict | No | If true, reject unknown fields and malformed expressions instead of dropping them | |
| expression | No | Single CAS expression to evaluate | |
| expressions | No | Optional ordered list of CAS expressions to evaluate in one isolated context (supports assignments across the batch) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose an important behavior: unsupported expressions return a GUI handoff link. It also adds context like 'headless', 'server-side', and 'MCP-only numeric mode', but does not mention success output format, error handling, or session/state behavior, leaving gaps for a mutation-capable tool.
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 exactly two sentences, front-loading the core purpose and adding the unsupported-expression behavior in the second sentence. No words are wasted, making it highly concise and well-structured.
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 schema is rich with parameter descriptions, but there is no output schema to clarify the return structure. The description explains the unsupported case (GUI handoff link) but not what a successful evaluation returns, leaving incomplete guidance for agents expecting numeric results. The sibling ambiguity also detracts from completeness.
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?
All three parameters (strict, expression, expressions) have descriptions in the schema, so schema coverage is 100%. The description's mention of 'one or more' aligns with the expression vs expressions distinction but adds no additional meaning beyond the schema, justifying the baseline score of 3.
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 clearly states the tool evaluates headless CAS expressions server-side, with a specific verb and resource. It mentions 'MCP-only numeric mode' to distinguish from GUI calculators, but does not explicitly differentiate from the sibling tool 'calculate_cas_headless', so it falls short of a 5.
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 for headless server-side numeric evaluation via MCP, and notes that unsupported expressions return a GUI handoff link. However, it does not explicitly state when to use this tool over alternative siblings like 'calculate' or 'calculate_cas_headless', so guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The three calculation tools (calculate, calculate_cas, calculate_cas_headless) overlap significantly, with calculate_cas_headless being an explicit alias of calculate_cas. An agent may struggle to choose between them. Other session tools are distinct, but the calculation ambiguity lowers the score.
Most tools follow a verb_noun pattern (list_calculators, create_session, get_session_state). Minor deviations exist, especially calculate_cas_headless with the 'headless' modifier and calculate lacking a noun, but the overall pattern is predictable.
With 10 tools, the count is reasonable for a calculator service with session management and CAS features. However, the presence of an alias tool (calculate_cas_headless) makes the set slightly redundant, though not overstuffed.
The surface covers core calculation, CAS evaluation, prefilled URL generation, and session lifecycle (create, push, get state, close). Minor gaps exist, such as no explicit session listing, but most workflows can be completed without workarounds.