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

No annotations, so the description must carry the full burden. It reveals that it computes three outputs (thickness, wrap dimensions, text eligibility) and supports multiple binding types, but does not explain return format, units, or how custom paper is handled beyond the schema.

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?

A single, front-loaded sentence with no wasted words. It is appropriately sized, though it could be tightened or expanded slightly for clarity without loss.

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 calculation tool with 7 parameters and no output schema, the description is minimally adequate: it names the computed outputs and binding types but omits units, expected input ranges, and what the outputs contain. It should do more given the lack of annotations and output schema.

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 the schema already documents all parameters with enums and defaults. The description adds no additional parameter meaning beyond listing the outcomes; baseline 3 is appropriate when schema does the heavy lifting.

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?

Clearly states a specific verb (calculates) and resources (spine thickness, wrap dimensions, spine text eligibility), with binding platforms named. Distinguishes from siblings like convert_paper_units and calculate_sheet_imposition_yield, though no explicit exclusions are given.

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?

No when-to-use guidance, prerequisites, or mention of alternatives. The description only states what it does, leaving the agent to infer context from the name and parameters.

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

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

No annotations are provided, so the description carries the full burden. The ream definition (500 sheets) and the freight CBM output add genuine domain context, but the description never states that this is a pure, deterministic, side-effect-free computation, nor that the tare allowance is opt-in via a parameter. For a read-only calculator the risk surface is low, but disclosure is still thin.

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?

A single efficient sentence that front-loads the calculation and enumerates outputs in a natural progression from unit weight to shipment freight. No filler, though the long compound output list makes it slightly dense.

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?

There is no output schema, but the description effectively enumerates the four return values, which is the most important gap to fill. Combined with 100% schema coverage on the five inputs, an agent has enough to call it correctly; only unit-assumption and determinism disclosures are 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 100%: gsm, sheet dimensions, quantity, and the include_carton_tare default are all documented in the schema with examples. The description adds only the ream=500 framing and the CBM output, so baseline 3 is appropriate.

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 names a specific verb (Calculates) and enumerates the exact outputs: single sheet weight, ream (500 sheets) weight, total production shipment weight, and freight CBM. This clearly separates it from calculator siblings like calculate_book_spine_width or convert_paper_units, though it never explicitly names an alternative or boundary.

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 phrase 'for paper runs' implies the context of use, and the output list implies it is the tool for weight/freight estimation. However, there is no explicit when-to-use, when-not-to-use, or routing guidance against the three sibling calculators (e.g. when to prefer convert_paper_units instead).

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

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

No annotations are provided, so the description carries the full behavioral burden. 'Computes' implies a side-effect-free calculation, and the description usefully names the three computed outputs, but it does not state assumptions such as whether item rotation/grain direction is handled or whether the result is deterministic and unit-consistent.

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?

A single front-loaded sentence with zero filler that states the operation and its outputs. Nothing is redundant with the name or schema.

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?

There is no output schema, so the description must cover return values; naming yield, utilization, and trim waste partially does this. Still, for a six-parameter geometry calculation with no annotations, it omits assumptions (rotation, grain, waste definition) and output format/units, leaving gaps an agent might need.

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 100%, so the schema already documents all six parameters (including defaults and example values for widths/heights). The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

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 specific verb ('Computes') plus the exact outputs (maximum item yield, sheet area utilization, trim waste) and the domain (cutting small items from large parent press sheets). This is clearly distinguishable from the siblings (spine width, unit conversion, paper weight), which cover unrelated print calculations.

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 stated scenario ('when cutting small items from large parent press sheets') implicitly tells the agent when the tool applies. However, there is no explicit when-not guidance and no mention of the sibling alternatives, so a human or agent is left to infer the fit.

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

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

With no annotations, the description carries the full behavioral burden. It does disclose a meaningful trait by naming 'authoritative ISO/TAPPI' standards as the conversion basis, which speaks to accuracy provenance. However, it omits precision/rounding behavior, error handling for incompatible unit families (e.g. caliper to weight), and the grade-dependence of basis-weight conversions, so transparency is only partial.

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?

A single front-loaded sentence that states the verb, the standards basis, and the three unit families with zero filler. Every clause earns its place.

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 3-parameter converter with full schema coverage and no output schema, the definition is minimally sufficient. It is missing the important caveat that basis-weight conversions are grade-dependent (Bond vs Book/Text vs Cover are already in the enum, implying this) and gives no hint of return format or precision, so it is adequate but not complete.

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 100% and both required unit parameters carry enums, so the schema already documents how to supply value/from_unit/to_unit. The description adds context on which unit families exist but no syntax or constraint detail beyond the schema, making the baseline 3 appropriate.

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 uses a specific verb ('Performs conversions') and resource (paper units), and enumerates the three unit families it spans: GSM, basis weight (Bond/Book/Text/Cover), and caliper. This clearly separates it from the sibling calculators, though it never names them explicitly, leaving the differentiation implicit.

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?

There is no when-to-use, when-not-to-use, or alternative-selection guidance. The agent can infer that this is the unit-conversion tool versus the spine/weight/imposition calculators, but that inference is never stated, and no prerequisites (e.g. needing a grade to convert basis weight) are given.

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