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

With no annotations, the description carries the full burden and does so richly: refusal of missing/blank required inputs, explicit blank/default handling for omissions, visibility truth-table and hidden-controller rules, retention of supplied hidden inputs with a not-applicable warning, and trust metadata with citation URL. It also flags that Model_Status/CHECK/STOP are load-bearing verdicts, which is essential behavioral context an agent could not infer.

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 purpose and return shape, but the body is a dense wall of edge-case prose (truth tables, hidden controllers, migration behavior) that is hard to scan. The critical 'read Model_Status' guidance is buried mid-paragraph rather than surfaced.

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?

No output schema exists, so the description must cover returns — and it does, specifying outputs keyed by named range, the status output, and a trust block with citation URL, resolvedInputs, and warnings. For a complex nested-input tool this is complete enough to invoke correctly.

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 100%, so baseline is 3, but the description adds real meaning: platform_version 'pins both validation and computation to that immutable version', and inputs must match the schema returned by get_calculator_schema, including exact table grid extents. This goes beyond the schema's own field descriptions.

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?

Opens with a specific verb+resource ('Run a calculator with the given inputs') and distinguishes itself from siblings by directing the agent to get_calculator_schema for input discovery. An agent can tell this is the execution tool versus the schema/search tools.

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?

Gives clear context: inspect get_calculator_schema first, platform_version pins an immutable version, missing required inputs are refused. It stops short of explicitly naming when NOT to use it or contrasting with siblings beyond the schema-lookup pointer, but the operational context is strong.

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