curve_from_pasted_table

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

With no annotations, the description carries the full behavioral burden and does so: it states 'No engine call; no arithmetic on the values,' identifies the id registration side effect, and documents edge-case behavior (the anchor point {reference_date: 1.0} added and reported in notes). It also discloses what the parse produces and how unparsed rows surface.

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-loads the one-line purpose before an Args block, and every sentence is load-bearing given thirteen undocumented parameters. The terse notation keps it dense without padding; nothing reads as filler.

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 high-complexity curve-construction tool with 13 params, 0% schema coverage, and no annotations, this covers input syntax, routing, provenance constraints, and return behavior. The output schema exists, yet the description still orients the agent to the return shape and notes without that being required.

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% across 13 parameters, so the description must compensate entirely — and it does, documenting text separators, accepted date formats, % and comma handling, per-row type tags, the three kind values, every market_data_source value, preset vs conventions, reference_date omission rules, quote_type fallback, percent, date_format inference, and compounding/frequency scope per kind.

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 and resource — it parses a user-pasted table and routes it to build_value_curve or build_curve — and explicitly names the two builder siblings, so an agent can distinguish it from them without opening a schema. The parenthetical examples (vendor screen, spreadsheet, ticket) make the input source unambiguous.

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 a clear use context and a strong explicit when-not rule: 'If you would have to invent numbers, do not call this tool: ask the user for the data,' plus a typology of market_data_source with the meaning of each value. It does not explicitly say when to prefer calling build_value_curve directly with clean values, so routing vs the sibling builders is left partly to inference.

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