SlangLane — Internet English, decoded.

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral value by stating 'Missing regional evidence is not invented' and emphasizing 'documented' notes, telling the agent the tool will not fabricate coverage gaps—a meaningful trait beyond 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?

Two tight sentences with no filler; the core behavior is front-loaded and the anti-fabrication caveat follows as useful second-position context. It could be marginally sharper about the exact-match constraint, but nothing is wasted.

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 one-parameter lookup with no output schema, the description does the important work of telling the agent what is returned (regional/register/disambiguation notes) and that gaps are not invented. It stops short of describing the response's shape or how multi-region notes are presented, but the core is covered.

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 parameter with 100% schema coverage, so the schema already documents 'term' (specifying 'Exact term or alias,' length bounds). The description's 'exact term' adds nothing beyond that, so the baseline of 3 for a fully-covered schema 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 gives a specific verb+resource: it returns 'documented regional, register, and disambiguation notes for an exact term,' which tells an agent exactly what content comes back. However, it never distinguishes itself from the sibling lookup_term, and the name 'compare_usage' implies cross-variant comparison that the single-term, notes-returning description does not explain.

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 explicit when-to-use, no when-not-to-use, and no named alternative among decode_phrase, lookup_term, search_terms, etc. The phrase 'for an exact term' is a soft input hint (use it for exact matches, not fuzzy search) but stops well short of routing guidance.

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, and closed-world, so the safety bar is met. The description adds genuine context beyond that: it preserves ambiguity rather than interpreting intent, and it discloses that text goes to a reference server and never to an LLM, which is a meaningful data-handling note.

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, front-loaded sentences, each carrying distinct information: purpose, behavioral stance, and data-handling. Zero 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?

With only two fully documented parameters and no output schema required (per rules, return values need not be explained), the description covers purpose, behavior, and privacy adequately. It is slightly thin on when to prefer this over sibling lookup tools, but otherwise 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%, so both parameters (text, include_mature) are already documented with constraints and defaults. The description adds no syntax or format detail about either parameter, so the baseline of 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 gives a specific verb+resource: 'Find documented slang in a phrase.' Combined with the name decode_phrase, an agent understands this is a decode/lookup operation. It does not explicitly distinguish itself from lookup_term or search_terms, so it is clear but not sibling-differentiated.

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?

'Preserves ambiguity; not an interpretation of speaker intent' implies when the tool is appropriate (documented reference lookup rather than intent inference), but it never names an alternative sibling or states an explicit when-not condition. Usage is inferable but not spelled out.

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, non-destructive, closed-world), so the bar is lower. The description adds that adult vocabulary is included via an optional filter, which hints at the default-true behavior, but says nothing about result ordering, page size behavior, or what happens when limit caps out at 20.

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 tight sentence with no padding, and the core purpose is front-loaded. The brevity, however, borders on under-specification rather than efficient concision given the tool's parameters.

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?

No output schema exists, so the description ought to convey what a 'dictionary summary' contains, but it does not. Combined with the undocumented limit parameter and no guidance on result ordering, the definition is minimally adequate rather than 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 only 50%: include_mature is documented in the schema, while limit has no description anywhere. The description's 'optional adult-language filter' merely restates what the schema already says about include_mature and adds nothing about the size/ordering semantics of limit.

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 ('Get recent published dictionary summaries') plus a secondary capability (adult-language filter), so the tool's function is clear. It does not, however, distinguish this from siblings like lookup_term or search_terms, so an agent must infer that 'recent' browsing is the differentiator.

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 explicit when-to-use guidance and no mention of alternatives among the five sibling tools. 'Recent published' implies a browse-latest use case, but the agent is left to infer when this beats search_terms or lookup_term.

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, and closed-world. The description contributes one real behavioral detail beyond them: results are restricted to "published" terms (drafts presumably excluded). Nothing is said about result size, ordering, or what happens for an unknown term.

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 filler; the scope qualifier comes before the input spec. Appropriately sized, though it is arguably terse enough that a short clause on output shape could be added without bloat.

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 full schema coverage and complete annotations, the main remaining gap is the return value: no output schema exists and the description doesn't say whether it returns a list, how many, or in what structure. Also silent on unmatched-term behavior. Adequate but with clear gaps.

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 the single `term` parameter is documented in the schema; the description's "exact term or alias" largely restates it. Baseline 3 applies since the schema carries the parameter semantics.

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?

Specific verb+resource ("Read ... related terms") with a stated scope ("published") and input form ("exact term or alias"). It is distinguishable from search_terms, but it never defines what "related" means (synonyms, translations, associations), leaving the payload somewhat ambiguous.

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 "exact term or alias" wording hints this is a precise lookup rather than a fuzzy search, which contrasts with search_terms. No explicit when-to-use/when-not, no named alternative, and no prerequisites.

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, not open-world). The description adds real behavioral context beyond them: what the response includes (sources, maturity, canonical URL, ambiguity) and the key constraint that it never synthesizes a meaning.

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, and the core action plus its constraint are front-loaded ahead of the return-value summary.

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 usefully enumerates the returned fields and the single, fully documented parameter. It is complete for a read tool with annotation coverage, though it omits ambiguity-resolution behavior and error/not-found handling.

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 schema already documents 'Exact term, slug, or alias'. The description restates the accepted forms without adding syntax, format, or validation detail, 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 ('look up') and a precise resource ('exact published slang term, slug, or alias'), and pinpoints the returned fields. It is distinguishable from siblings: 'exact' separates it from search_terms, and 'Never generates a meaning' separates it from decode_phrase.

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 word 'exact' implies you must already know the term, and 'Never generates a meaning' hints at when to reach for decode_phrase instead. However, no sibling is named and there is no explicit when-to-use/when-not statement, so routing is left to inference.

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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile and closed-world scope are covered. The description's "no web search" largely restates openWorldHint=false, though "no generation" adds a small clarifying note; nothing is said about result ordering, pagination, or result shape.

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, front-loaded sentences with no filler; the core capability comes first and the scope caveat second. The second sentence is terse to the point of being slightly cryptic, which keeps it just short of ideal.

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, no-output-schema search tool with safety annotations already in place, the description covers what it does but omits result format, ordering, and sibling routing. An agent could call it, but would be guessing on selection between the five sibling retrieval 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 description coverage is 67% (query and include_mature are documented, limit is not). The description's mention of names/aliases/summaries indirectly hints at what the query matches against, which is modest added meaning, but it never addresses limit, defaults, or the mature-content flag. 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?

States a specific verb (search) and the fields it covers (published names, aliases, summaries), so the agent knows this is a text-match tool over term entries. It does not name or contrast with the nearest siblings (lookup_term, get_recent_terms, get_related_terms), leaving that differentiation to inference.

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 web search or generation" gives a useful when-not boundary, telling the agent this only queries an internal published index. However, there is no positive guidance on when to pick this over lookup_term (exact lookup) or get_related_terms (relationship traversal), so usage is only implied.

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