Tachtien

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

The annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds two genuinely useful facts beyond that: the output content is in Dutch and it mirrors the tachtien.nl entry. It says nothing about length or caching, which is acceptable given the low-risk read profile.

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 tight sentences with zero filler. The target word and the returned fields are front-loaded, and the output-language note is a short, purposeful trailing sentence.

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?

An output schema exists, so return values need no explanation, and the description still previews them helpfully. For a fixed-target, parameterless lookup this is essentially complete; only the implicit 'this tool always defines tachtien' framing could be made more explicit.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline is 4. One small missed opportunity is stating explicitly that no word argument is accepted, which would stop an agent from attempting to define other terms.

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 (define) and a specific resource (the Dutch word 'tachtien'), and enumerates the fields returned: syllables, part of speech, IPA, definition and origin. That is enough to distinguish it from 'examples', 'mentions' and 'tachtienify', though no sibling is named explicitly.

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?

Usage is only implied: an agent infers it should call this when it wants the dictionary entry for 'tachtien'. There is no statement of when not to use it, no pointer to the sibling tools for usages/mentions, and no note that the target word is fixed rather than passed in.

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, destructiveHint=false and openWorldHint=false, so safety and determinism are covered. The description adds the useful detail that each example is a dialogue of one or more lines, but says nothing about how many examples come back, ordering, or whether the corpus is fixed.

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 short sentences, front-loaded with what is returned and immediately followed by the shape of each item. No filler, no restatement of the tool name beyond what is needed to identify the target word.

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 an output schema present and rich annotations, the description only needs to frame the content, which it does by naming the target word, the language and the item structure. Minor gaps (expected result count, whether the word is fixed) keep it short of full completeness for a tool with no required parameters.

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?

There is a single optional parameter whose schema description already fully explains the random behavior (100% coverage), so the schema carries the semantics. The description does not mention the random option or the default all-examples behavior, so it adds nothing beyond structured data here.

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 resource — example sentences using the word 'tachtien', in Dutch — and describes their shape (short dialogues of one or more lines). It does not explicitly contrast itself with siblings like define, mentions or tachtienify, so an agent must infer that this tool returns illustrative usage rather than definitions or occurrence lists.

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?

Usage is only implied: an agent can guess this is for seeing the word in context, but there is no explicit when-to-use statement, no exclusions, and no named alternative such as define (for meaning) or mentions (for occurrences). The sibling set makes such routing guidance genuinely valuable and it is absent.

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 a safe, read-only, idempotent, closed-world call, so the safety profile is covered. The description goes further by disclosing the actual decision logic (18 is achttien, 80 is tachtig, 'meer dan 50' counts, negation makes either false) and that the response includes a Dutch-language reason. It says nothing about behavior for edge inputs such as zero, negatives, or malformed strings.

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?

One paragraph, front-loaded with the core judgment before the rule list, and every clause carries a distinct rule. It is dense with parenthetical examples, which makes it slower to scan than it could be, but no sentence is 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?

An output schema exists, so the return value needs no explanation, and annotations cover the safety profile; what remains for the description is the judgment policy, which it covers thoroughly. Minor gaps are edge cases (zero, negative numbers, plain 'tachtig' vs 'tachtien' spelling) and the absence of any pointer to sibling tools.

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% and the single parameter already has examples, so the baseline would be 3. The description earns more by explaining what the schema cannot: that the string form may be vague ('heel veel', 'geen idee'), that lower-bound phrases are accepted ('100+', 'meer dan 50'), and that negation is semantically meaningful rather than just text.

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 opens with a specific verb+resource: judge whether an amount counts as 'tachtien', plus the output form (a tongue-in-cheek reason in Dutch). That is far clearer than the name alone, which is opaque without the gloss '(uncountably many)'. It does not, however, name or contrast any sibling (define, examples, mentions, tachtienify), so the agent gets no explicit differentiation.

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 lays out the classification criteria in detail: exact numbers never count, vague amounts do, estimates of 50+ count, negation flips the result. That is strong guidance on how the tool decides. What is missing is routing guidance — nothing says when to pick this over tachtienify or define, or what to do for amounts outside the stated cases.

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, non-destructive and closed-world, so the safety profile is covered. The description adds one useful behavioral nuance — that url is null when a mention has no link — but says nothing about result ordering, volume, or pagination, so it adds some value without being rich.

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 short sentences, scope stated first, the null-URL caveat second. Nothing is redundant and nothing needs to be re-read.

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 zero-required-parameter listing tool with a documented enum and an existing output schema, the description covers purpose, scope, and the main edge case (null URL). Only minor operational details — ordering and result size — are absent, and the output schema plus annotations absorb most of that burden.

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?

The single optional 'source' parameter has 100% schema description coverage and an enum of twitter/press/cityguys, so the schema carries the semantic load. The description adds nothing beyond it (no note that omitting source returns all sources), which is the expected baseline here.

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 the resource precisely ('external mentions of tachtien') and enumerates the sub-kinds (tweets, press, Cityguys articles) plus returned fields (title, source, URL), so an agent knows exactly what it retrieves. It does not explicitly contrast with siblings, but define/examples/is_tachtien/tachtienify are unrelated enough that differentiation is not a real risk.

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?

Usage is only implied: the description makes clear this lists mentions, but it gives no when-to-use condition, no exclusion, and no mention of ordering, limits, or whether the list is exhaustive. For a simple read tool with an optional filter, that is the minimum viable level rather than a genuine gap.

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 readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real value by disclosing the substitution rules, the preservation carve-outs, and the shape of the result (new text, replacement count, per-phrase index). The return-value sentence partly duplicates the output schema, which holds it just below a 5.

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 tight sentences, front-loaded with the action and the transformation rule, followed by the exclusion rule and the return shape. No filler and no restatement of the name or title.

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?

Output schema exists, so return values need little explanation, and the transformation rules and exclusions are well covered. The remaining softness is that 'large estimate' vs 'small estimate' is defined only by example, and the term 'tachtien' itself is never characterized – an agent must infer it from sibling tools.

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% with a single documented parameter ('The text to rewrite', 1–5000 chars), so the schema carries the parameter semantics. The description adds no constraints beyond it (e.g. what happens on truncation at 5000 chars), 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?

States a specific verb (rewrite) plus the exact resource (a Dutch/English text) and the precise transformation target: vague large amounts and large estimates become 'tachtien'. Concrete examples of both matched and preserved phrases make it unmistakable against siblings like is_tachtien (check) or mentions (find).

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?

Clearly scopes when the tool applies by defining what is rewritten and explicitly what is not ('Exact numbers, small estimates and years are left alone'). It does not, however, name an alternative sibling or state when to prefer is_tachtien/mentions instead, so the routing guidance is implicit rather than explicit.

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