Wiskundehulp

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral detail beyond that: unpaginated full listing of id/modes/fields, plus the fact that a calculator=<id> query enriches the response with field hints and an example input. It doesn't discuss size limits or ordering, but the useful extras are there.

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?

Three short sentences, front-loaded with the core listing behavior and then the optional enrichment, then the workflow tip. Nothing is redundant with the title and no sentence could be cut without losing information.

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 carry the return-value burden, and it does: it names the exact fields returned both in the base and calculator-filtered cases. For a two-parameter, all-optional, read-only discovery tool this is sufficient to call 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 genuinely adds meaning beyond the schema's terse "Optional: only show this calculator id" by explaining the payoff of that parameter (field hints and an example input). The language parameter is left to the schema, which is acceptable given its enum and default are self-explanatory.

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 ("List every calculator") and immediately enumerates the surface it exposes: id, modes, input fields. The variant behavior with calculator=<id> and the routing sentence toward run_calculator make it unambiguous against the nearest sibling.

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?

"Call this before run_calculator" gives an explicit prerequisite and ordering, which is strong when-to-use guidance. It stops short of covering the other sibling (solve_math_question) or any when-not condition, so it isn't a full 5.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false. The description adds useful behavioral context beyond annotations: it returns worked steps, accepts unit values via inputs.unit, and defines input value encodings. It does not contradict the annotations.

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 a single dense paragraph with the purpose front-loaded, followed by practical input-format examples. Every sentence adds usable information without repetition or 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 tool with nested inputs and no output schema, the description covers the call-critical details: calculator id source, input value formats, unit handling, and the fact that worked steps are returned. A minor gap is that it does not explicitly state where per-calculator field ids and modes are discovered, though list_calculators is implied.

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 documents calculator, mode, inputs, and language. The description adds meaningful semantics beyond the schema for the nested inputs object, explaining how number, fraction, list, text, and unit values should be encoded. It leaves mode and language details to 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 description states a specific verb and resource: run one calculator using an id from list_calculators with explicit inputs, and return the answer with worked steps. It clearly separates this from the listing tool, but does not explicitly differentiate it from the other sibling, solve_math_question.

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 gives clear usage context: obtain calculator ids from list_calculators and provide explicit inputs. It does not state when not to use this tool or when solve_math_question would be the better alternative.

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?

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), so the description earns credit for adding genuine behavior: worked steps are returned, unsupported input yields an explicit refusal with nearest-topic suggestions, and it 'never guesses'. It doesn't add much else, but for a read-only tool this is solid added context.

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?

Two sentences, front-loaded with purpose, then scope, then failure mode. The topic enumeration is lengthy but earns its place by defining what is and isn't supported; nothing is padding.

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?

With no output schema, the description correctly carries the return-value burden ('answer with worked steps') and the error path. Only the shape of the worked-steps response is left unspecified, which is a minor gap for a low-complexity tool.

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 both parameters are already documented, including the nl/en enum and the 240-char cap. The description reinforces the Dutch-or-English input and the 'short' constraint but adds no syntax or format detail beyond the schema examples.

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?

A specific verb+resource pair ('Solve a short maths question... return the answer with worked steps') with a concrete topic list that bounds scope precisely. It does not explicitly distinguish itself from run_calculator, so an agent has to infer that this one handles word problems/equations while the sibling presumably evaluates raw expressions.

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 when it applies (short Dutch/English maths questions in the enumerated topics) and tells what happens when the question falls outside that scope. But it never names run_calculator or list_calculators as alternatives, nor states when to prefer one over the other.

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