tolerance_cost_check

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

With no annotations to lean on, the description carries the full behavioral burden and does so richly: it defines the three verdict values and what 'needs_secondary_operation' means, explains the cost-doubling-per-1.5-IT-grade behavior, clarifies that ratios (not absolutes) are defensible, and discloses the fidelity='correlation'/band_pct=50 caveat plus the escalate_to hint. This is far more than structured fields provide.

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?

Purpose is front-loaded in the first sentence and the dense technical content (IT grade mapping, cost behavior, return fields) is well organized. It is long and prose-heavy with several parenthetical digressions, so it is efficient rather than maximally tight.

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 6-parameter analysis tool with no output schema, the description supplies the full return shape ({process, links:[...], n_links, total_cost_index, mean_cost_index, flagged, pass, fidelity, band_pct, basis, escalate_to}) and the per-link field semantics (it_grade, cost_index, verdict, cheapest_operation, natural_it). Nothing an agent needs to call or interpret the result is missing.

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 and it does: it documents `chain` format and its relationship to tolerance_stackup's chain, the live `handle` (+ axis, default_tol, general) alternative, and enumerates all `process` values (cnc | injection | casting | sheet | fdm | drilling | ...). All six parameters are given meaning absent from the schema.

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 opening line states a specific verb+resource ('Price a tolerance scheme against the process that has to hold it') and explicitly positions the tool relative to two siblings, tolerance_stackup ('what tolerance works') and cost_estimate ('what does it cost'). An agent can tell exactly what this does and how it differs from neighboring 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?

It clearly states the context of use — the 'missing link' between tolerance_stackup and cost_estimate — and the metrics paragraph explains when the results matter (`pass` is false when any link flags). It stops short of explicit when-not-to-use guidance or a direct 'use X instead' routing statement, so it falls just below the top.

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